state/agent/agent.log

[2026-09-20 07:29:35] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 07:29:43] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 07:29:45] autostart default profile=fast
[2026-09-20 07:29:45] starting profile=fast engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 07:29:45] $ /opt/hf/bin/hf download bloomer010/Ling-3.0-tiny-GGUF Ling-3.0-tiny-Q4_K_M.gguf --local-dir /mnt/data/models/Ling-3.0-tiny-GGUF --max-workers 4
[2026-09-20 07:29:59] GGUF download verified file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 07:29:59] engine pid=9602 engine=llama.cpp cpus=2
[2026-09-20 07:30:50] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 07:30:51] starting profile=fast engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 07:30:51] GGUF cache verified repo=bloomer010/Ling-3.0-tiny-GGUF file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 07:30:51] engine pid=893 engine=llama.cpp cpus=2
[2026-09-20 07:31:37] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 07:31:39] autostart default profile=fast
[2026-09-20 07:31:39] starting profile=fast engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 07:31:39] GGUF cache verified repo=bloomer010/Ling-3.0-tiny-GGUF file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 07:31:39] engine pid=1232 engine=llama.cpp cpus=2
[2026-09-20 07:33:02] stopping proxy pid=896
[2026-09-20 07:33:02] start cancelled profile=fast
[2026-09-20 07:33:02] stopping engine pid=893
[2026-09-20 07:33:11] stopping proxy pid=9603
[2026-09-20 07:33:11] stopping engine pid=9602
[2026-09-20 07:33:11] start cancelled profile=fast
[2026-09-20 07:33:11] local agent manager shutting down
[2026-09-20 07:33:11] local agent manager shutting down
[2026-09-20 07:33:13] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 07:33:15] autostart default profile=fast
[2026-09-20 07:33:15] starting profile=fast engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 07:33:15] GGUF cache verified repo=bloomer010/Ling-3.0-tiny-GGUF file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 07:33:15] engine pid=12874 engine=llama.cpp cpus=2
[2026-09-20 07:33:33] local agent ready engine=llama.cpp elapsed=18.01s
[2026-09-20 07:34:05] KV save before stop: saved=True tokens=4550 bytes=36982440
[2026-09-20 07:34:05] stopping proxy pid=12875
[2026-09-20 07:34:05] stopping engine pid=12874
[2026-09-20 07:34:05] local agent manager shutting down
[2026-09-20 07:34:05] local agent manager shutting down
[2026-09-20 07:34:08] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 07:34:10] autostart default profile=fast
[2026-09-20 07:34:10] starting profile=fast engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 07:34:10] GGUF cache verified repo=bloomer010/Ling-3.0-tiny-GGUF file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 07:34:10] engine pid=13687 engine=llama.cpp cpus=2
[2026-09-20 07:34:16] local agent ready engine=llama.cpp elapsed=5.90s
[2026-09-20 07:34:37] KV save before stop: saved=True tokens=4550 bytes=36982440
[2026-09-20 07:34:37] stopping proxy pid=34373
[2026-09-20 07:34:37] stopping engine pid=34372
[2026-09-20 07:34:38] local agent manager shutting down
[2026-09-20 07:34:38] local agent manager shutting down
[2026-09-20 07:34:40] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 07:34:42] autostart default profile=fast
[2026-09-20 07:34:42] starting profile=fast engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 07:34:42] GGUF cache verified repo=bloomer010/Ling-3.0-tiny-GGUF file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 07:34:42] engine pid=34875 engine=llama.cpp cpus=2
[2026-09-20 07:34:49] local agent ready engine=llama.cpp elapsed=7.35s
[2026-09-20 07:34:53] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 07:34:55] autostart default profile=fast
[2026-09-20 07:34:55] starting profile=fast engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 07:34:55] GGUF cache verified repo=bloomer010/Ling-3.0-tiny-GGUF file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 07:34:55] engine pid=1252 engine=llama.cpp cpus=2
[2026-09-20 07:35:07] local agent ready engine=llama.cpp elapsed=11.67s
[2026-09-20 07:35:33] KV save before stop: saved=True tokens=4550 bytes=36982440
[2026-09-20 07:35:33] stopping proxy pid=14224
[2026-09-20 07:35:33] stopping engine pid=14223
[2026-09-20 07:35:34] local agent manager shutting down
[2026-09-20 07:35:34] local agent manager shutting down
[2026-09-20 07:35:36] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 07:35:38] autostart default profile=fast
[2026-09-20 07:35:38] starting profile=fast engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 07:35:38] GGUF cache verified repo=bloomer010/Ling-3.0-tiny-GGUF file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 07:35:38] engine pid=15088 engine=llama.cpp cpus=2
[2026-09-20 07:35:43] local agent ready engine=llama.cpp elapsed=4.86s
[2026-09-20 07:36:04] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 07:36:05] starting profile=fast engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 07:36:05] GGUF cache verified repo=bloomer010/Ling-3.0-tiny-GGUF file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 07:36:05] engine pid=916 engine=llama.cpp cpus=2
[2026-09-20 07:36:07] ERROR PermissionError: [Errno 13] Permission denied: '/tmp/local-agent-models/.Ling-3.0-tiny-Q4_K_M.gguf.part'
[2026-09-20 07:36:07] stopping proxy pid=918
[2026-09-20 07:36:07] stopping engine pid=916
[2026-09-20 07:36:39] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 07:36:41] autostart default profile=fast
[2026-09-20 07:36:41] starting profile=fast engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 07:36:41] GGUF cache verified repo=bloomer010/Ling-3.0-tiny-GGUF file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 07:36:41] engine pid=1266 engine=llama.cpp cpus=2
[2026-09-20 07:36:54] local agent ready engine=llama.cpp elapsed=12.63s
[2026-09-20 07:39:13] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 07:39:15] autostart default profile=fast
[2026-09-20 07:39:15] starting profile=fast engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 07:39:15] GGUF cache verified repo=bloomer010/Ling-3.0-tiny-GGUF file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 07:39:15] engine pid=1253 engine=llama.cpp cpus=2
[2026-09-20 07:39:26] local agent ready engine=llama.cpp elapsed=10.63s
[2026-09-20 07:40:21] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 07:40:23] autostart default profile=fast
[2026-09-20 07:40:23] starting profile=fast engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 07:40:23] GGUF cache verified repo=bloomer010/Ling-3.0-tiny-GGUF file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 07:40:23] engine pid=1271 engine=llama.cpp cpus=2
[2026-09-20 07:40:33] local agent ready engine=llama.cpp elapsed=10.12s
[2026-09-20 07:41:12] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 07:41:14] autostart default profile=fast
[2026-09-20 07:41:14] starting profile=fast engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 07:41:14] GGUF cache verified repo=bloomer010/Ling-3.0-tiny-GGUF file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 07:41:14] engine pid=1267 engine=llama.cpp cpus=2
[2026-09-20 07:41:25] local agent ready engine=llama.cpp elapsed=10.47s
[2026-09-20 07:49:48] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 07:49:50] autostart default profile=fast
[2026-09-20 07:49:50] starting profile=fast engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 07:49:50] GGUF cache verified repo=bloomer010/Ling-3.0-tiny-GGUF file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 07:49:50] engine pid=1192 engine=llama.cpp cpus=2
[2026-09-20 07:50:08] local agent ready engine=llama.cpp elapsed=18.79s
[2026-09-20 07:52:17] KV save before stop: saved=True tokens=4550 bytes=36982440
[2026-09-20 07:52:17] stopping proxy pid=35678
[2026-09-20 07:52:17] stopping engine pid=35677
[2026-09-20 07:52:18] local agent manager shutting down
[2026-09-20 07:52:18] local agent manager shutting down
[2026-09-20 07:52:20] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 07:52:22] autostart default profile=fast
[2026-09-20 07:52:22] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 07:52:22] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 07:52:22] engine pid=47712 engine=llama.cpp cpus=2
[2026-09-20 07:52:23] ERROR PermissionError: [Errno 13] Permission denied: '/tmp/local-agent-models/.Qwen3-1.7B-Q4_K_M.gguf.part'
[2026-09-20 07:52:23] stopping proxy pid=47713
[2026-09-20 07:52:23] stopping engine pid=47712
[2026-09-20 07:52:30] local agent ready engine=llama.cpp elapsed=8.23s
[2026-09-20 07:53:12] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 07:53:14] autostart default profile=fast
[2026-09-20 07:53:14] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 07:53:14] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 07:53:14] engine pid=1532 engine=llama.cpp cpus=2
[2026-09-20 07:53:27] local agent ready engine=llama.cpp elapsed=13.95s
[2026-09-20 07:53:30] KV save before stop: saved=True tokens=26 bytes=839788
[2026-09-20 07:53:30] stopping proxy pid=1534
[2026-09-20 07:53:30] stopping engine pid=1532
[2026-09-20 07:55:48] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 07:55:50] autostart default profile=fast
[2026-09-20 07:55:50] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 07:55:50] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 07:55:50] engine pid=1238 engine=llama.cpp cpus=2
[2026-09-20 07:56:02] local agent ready engine=llama.cpp elapsed=12.22s
[2026-09-20 07:57:10] local agent manager shutting down
[2026-09-20 07:57:10] local agent manager shutting down
[2026-09-20 07:57:12] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 07:57:14] autostart default profile=fast
[2026-09-20 07:57:14] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 07:57:14] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 07:57:14] engine pid=50021 engine=llama.cpp cpus=2
[2026-09-20 07:57:23] local agent ready engine=llama.cpp elapsed=8.71s
[2026-09-20 07:57:50] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 07:57:52] autostart default profile=fast
[2026-09-20 07:57:52] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 07:57:52] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 07:57:52] engine pid=1599 engine=llama.cpp cpus=2
[2026-09-20 07:57:56] local agent ready engine=llama.cpp elapsed=3.35s
[2026-09-20 07:57:59] KV save before stop: saved=True tokens=26 bytes=839788
[2026-09-20 07:57:59] stopping proxy pid=1600
[2026-09-20 07:57:59] stopping engine pid=1599
[2026-09-20 08:00:01] KV save before stop: saved=True tokens=26 bytes=839788
[2026-09-20 08:00:01] stopping proxy pid=50022
[2026-09-20 08:00:01] stopping engine pid=50021
[2026-09-20 08:00:01] local agent manager shutting down
[2026-09-20 08:00:01] local agent manager shutting down
[2026-09-20 08:00:03] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 08:00:05] autostart default profile=fast
[2026-09-20 08:00:05] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 08:00:05] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 08:00:05] engine pid=50804 engine=llama.cpp cpus=2
[2026-09-20 08:00:09] local agent ready engine=llama.cpp elapsed=3.39s
[2026-09-20 08:00:21] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 08:00:23] autostart default profile=fast
[2026-09-20 08:00:23] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 08:00:23] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 08:00:23] engine pid=1519 engine=llama.cpp cpus=2
[2026-09-20 08:00:27] local agent ready engine=llama.cpp elapsed=4.07s
[2026-09-20 08:00:31] KV save before stop: saved=True tokens=26 bytes=839788
[2026-09-20 08:00:31] stopping proxy pid=1520
[2026-09-20 08:00:31] stopping engine pid=1519
[2026-09-20 08:03:55] KV save before stop: saved=True tokens=26 bytes=839788
[2026-09-20 08:03:55] stopping proxy pid=1879
[2026-09-20 08:03:55] stopping engine pid=1878
[2026-09-20 08:03:55] local agent manager shutting down
[2026-09-20 08:03:55] local agent manager shutting down
[2026-09-20 08:03:57] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 08:03:59] autostart default profile=fast
[2026-09-20 08:03:59] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 08:03:59] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 08:03:59] engine pid=3086 engine=llama.cpp cpus=2
[2026-09-20 08:04:02] local agent ready engine=llama.cpp elapsed=2.61s
[2026-09-20 08:04:11] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 08:04:13] autostart default profile=fast
[2026-09-20 08:04:13] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 08:04:13] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 08:04:13] engine pid=1510 engine=llama.cpp cpus=2
[2026-09-20 08:04:16] local agent ready engine=llama.cpp elapsed=2.83s
[2026-09-20 08:04:18] KV save before stop: saved=True tokens=26 bytes=839788
[2026-09-20 08:04:18] stopping proxy pid=1511
[2026-09-20 08:04:18] stopping engine pid=1510
[2026-09-20 08:19:19] KV save before stop: saved=True tokens=3787 bytes=122214780
[2026-09-20 08:19:19] stopping proxy pid=3087
[2026-09-20 08:19:19] stopping engine pid=3086
[2026-09-20 08:19:20] local agent manager shutting down
[2026-09-20 08:19:20] local agent manager shutting down
[2026-09-20 08:19:22] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 08:19:24] autostart default profile=fast
[2026-09-20 08:19:24] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 08:19:24] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 08:19:24] engine pid=6398 engine=llama.cpp cpus=2
[2026-09-20 08:19:27] local agent ready engine=llama.cpp elapsed=3.14s
[2026-09-20 08:21:16] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 08:21:18] autostart default profile=fast
[2026-09-20 08:21:18] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 08:21:18] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 08:21:18] engine pid=459 engine=llama.cpp cpus=2
[2026-09-20 08:21:24] local agent ready engine=llama.cpp elapsed=6.10s
[2026-09-20 08:22:03] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 08:22:05] autostart default profile=fast
[2026-09-20 08:22:05] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 08:22:05] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 08:22:05] engine pid=226 engine=llama.cpp cpus=2
[2026-09-20 08:22:13] local agent ready engine=llama.cpp elapsed=7.95s
[2026-09-20 08:22:28] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 08:22:30] autostart default profile=fast
[2026-09-20 08:22:30] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 08:22:30] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 08:22:30] engine pid=389 engine=llama.cpp cpus=2
[2026-09-20 08:22:36] local agent ready engine=llama.cpp elapsed=5.64s
[2026-09-20 08:23:26] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 08:23:26] starting profile=long engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 08:23:26] GGUF cache verified repo=bloomer010/Ling-3.0-tiny-GGUF file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 08:23:26] engine pid=344 engine=llama.cpp cpus=2
[2026-09-20 08:23:48] local agent ready engine=llama.cpp elapsed=22.14s
[2026-09-20 08:53:49] KV save before stop: saved=True tokens=26 bytes=839788
[2026-09-20 08:53:49] stopping proxy pid=54360
[2026-09-20 08:53:49] stopping engine pid=54359
[2026-09-20 08:53:50] local agent manager shutting down
[2026-09-20 08:53:50] local agent manager shutting down
[2026-09-20 08:53:52] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 08:53:54] autostart default profile=fast
[2026-09-20 08:53:54] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 08:53:54] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 08:53:54] engine pid=60806 engine=llama.cpp cpus=2
[2026-09-20 08:53:57] local agent ready engine=llama.cpp elapsed=3.12s
[2026-09-20 08:54:38] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 08:54:40] autostart default profile=fast
[2026-09-20 08:54:40] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 08:54:40] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 08:54:40] engine pid=1661 engine=llama.cpp cpus=2
[2026-09-20 08:54:46] local agent ready engine=llama.cpp elapsed=5.96s
[2026-09-20 08:54:47] KV save before stop: saved=True tokens=26 bytes=839788
[2026-09-20 08:54:47] stopping proxy pid=1662
[2026-09-20 08:54:47] stopping engine pid=1661
[2026-09-20 08:54:48] starting profile=long engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 08:54:48] GGUF cache verified repo=bloomer010/Ling-3.0-tiny-GGUF file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 08:54:48] engine pid=2709 engine=llama.cpp cpus=2
[2026-09-20 08:55:07] local agent ready engine=llama.cpp elapsed=19.05s
[2026-09-20 08:56:57] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 08:56:59] autostart default profile=fast
[2026-09-20 08:56:59] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 08:56:59] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 08:56:59] engine pid=1391 engine=llama.cpp cpus=2
[2026-09-20 08:57:04] local agent ready engine=llama.cpp elapsed=5.26s
[2026-09-20 08:58:27] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 08:58:29] autostart default profile=fast
[2026-09-20 08:58:29] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 08:58:29] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 08:58:29] engine pid=1261 engine=llama.cpp cpus=2
[2026-09-20 08:58:33] local agent ready engine=llama.cpp elapsed=4.59s
[2026-09-20 08:59:21] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 08:59:23] autostart default profile=fast
[2026-09-20 08:59:23] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 08:59:23] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 08:59:23] engine pid=1265 engine=llama.cpp cpus=2
[2026-09-20 08:59:27] local agent ready engine=llama.cpp elapsed=4.66s
[2026-09-20 09:04:01] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 09:04:03] autostart default profile=fast
[2026-09-20 09:04:03] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 09:04:03] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 09:04:03] engine pid=1101 engine=llama.cpp cpus=2
[2026-09-20 09:04:09] local agent ready engine=llama.cpp elapsed=6.06s
[2026-09-20 09:05:22] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 09:05:24] autostart default profile=fast
[2026-09-20 09:05:24] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 09:05:24] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 09:05:24] engine pid=1287 engine=llama.cpp cpus=2
[2026-09-20 09:05:29] local agent ready engine=llama.cpp elapsed=5.16s
[2026-09-20 09:07:23] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 09:07:25] autostart default profile=fast
[2026-09-20 09:07:25] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 09:07:25] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 09:07:25] engine pid=1686 engine=llama.cpp cpus=2
[2026-09-20 09:07:30] local agent ready engine=llama.cpp elapsed=5.45s
[2026-09-20 09:08:13] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 09:08:15] autostart default profile=fast
[2026-09-20 09:08:15] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 09:08:15] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 09:08:15] engine pid=1280 engine=llama.cpp cpus=2
[2026-09-20 09:08:20] local agent ready engine=llama.cpp elapsed=5.32s
[2026-09-20 09:09:14] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 09:09:16] autostart default profile=fast
[2026-09-20 09:09:16] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 09:09:16] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 09:09:16] engine pid=1141 engine=llama.cpp cpus=2
[2026-09-20 09:09:23] local agent ready engine=llama.cpp elapsed=6.62s
[2026-09-20 09:10:29] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 09:10:29] starting profile=long engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 09:10:29] GGUF cache verified repo=bloomer010/Ling-3.0-tiny-GGUF file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 09:10:29] engine pid=645 engine=llama.cpp cpus=2
[2026-09-20 09:10:50] local agent ready engine=llama.cpp elapsed=20.90s
[2026-09-20 09:11:38] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 09:11:38] starting profile=long engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 09:11:38] GGUF cache verified repo=bloomer010/Ling-3.0-tiny-GGUF file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 09:11:38] engine pid=637 engine=llama.cpp cpus=2
[2026-09-20 09:11:57] local agent ready engine=llama.cpp elapsed=19.18s
[2026-09-20 09:12:41] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 09:12:41] starting profile=long engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 09:12:41] GGUF cache verified repo=bloomer010/Ling-3.0-tiny-GGUF file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 09:12:41] engine pid=732 engine=llama.cpp cpus=2
[2026-09-20 09:13:00] local agent ready engine=llama.cpp elapsed=18.78s
[2026-09-20 09:15:32] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 09:15:34] autostart default profile=fast
[2026-09-20 09:15:34] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 09:15:34] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 09:15:34] engine pid=996 engine=llama.cpp cpus=2
[2026-09-20 09:15:40] local agent ready engine=llama.cpp elapsed=6.04s
[2026-09-20 09:17:01] KV save before stop: saved=True tokens=26 bytes=839788
[2026-09-20 09:17:01] stopping proxy pid=997
[2026-09-20 09:17:01] stopping engine pid=996
[2026-09-20 09:17:02] starting profile=long engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 09:17:02] GGUF cache verified repo=bloomer010/Ling-3.0-tiny-GGUF file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 09:17:02] engine pid=10172 engine=llama.cpp cpus=2
[2026-09-20 09:17:20] local agent ready engine=llama.cpp elapsed=17.47s
[2026-09-20 10:35:40] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-20 10:35:42] autostart default profile=fast
[2026-09-20 10:35:42] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-20 10:35:42] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-20 10:35:42] engine pid=976 engine=llama.cpp cpus=2
[2026-09-20 10:35:49] local agent ready engine=llama.cpp elapsed=7.02s
[2026-09-20 10:40:12] KV save before stop: saved=True tokens=26 bytes=839788
[2026-09-20 10:40:12] stopping proxy pid=977
[2026-09-20 10:40:12] stopping engine pid=976
[2026-09-20 10:40:13] starting profile=long engine=llama.cpp repo=bloomer010/Ling-3.0-tiny-GGUF
[2026-09-20 10:40:13] GGUF cache verified repo=bloomer010/Ling-3.0-tiny-GGUF file=/mnt/data/models/Ling-3.0-tiny-GGUF/Ling-3.0-tiny-Q4_K_M.gguf size=4823895104
[2026-09-20 10:40:13] engine pid=24750 engine=llama.cpp cpus=2
[2026-09-20 10:40:34] local agent ready engine=llama.cpp elapsed=21.59s
[2026-09-21 00:06:22] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-21 00:06:24] autostart default profile=fast
[2026-09-21 00:06:24] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-21 00:06:24] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-21 00:06:24] engine pid=1006 engine=llama.cpp cpus=2
[2026-09-21 00:06:31] local agent ready engine=llama.cpp elapsed=7.03s
[2026-09-22 13:07:49] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-22 13:07:51] autostart default profile=fast
[2026-09-22 13:07:51] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-22 13:07:51] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-22 13:07:51] engine pid=874 engine=llama.cpp cpus=2
[2026-09-22 13:07:59] local agent ready engine=llama.cpp elapsed=8.15s
[2026-09-22 13:09:51] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-22 13:09:53] autostart default profile=fast
[2026-09-22 13:09:53] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-22 13:09:53] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-22 13:09:53] engine pid=783 engine=llama.cpp cpus=2
[2026-09-22 13:10:01] local agent ready engine=llama.cpp elapsed=8.30s
[2026-09-22 16:56:09] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-22 16:56:11] autostart default profile=fast
[2026-09-22 16:56:11] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-22 16:56:11] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-22 16:56:11] engine pid=1009 engine=llama.cpp cpus=2
[2026-09-22 16:56:17] local agent ready engine=llama.cpp elapsed=5.73s
[2026-09-22 16:59:49] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-22 16:59:51] autostart default profile=fast
[2026-09-22 16:59:51] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-22 16:59:51] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-22 16:59:51] engine pid=553 engine=llama.cpp cpus=2
[2026-09-22 16:59:59] local agent ready engine=llama.cpp elapsed=8.19s
[2026-09-22 17:02:43] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-22 17:02:45] autostart default profile=fast
[2026-09-22 17:02:45] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-22 17:02:45] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-22 17:02:45] engine pid=461 engine=llama.cpp cpus=2
[2026-09-22 17:02:59] local agent ready engine=llama.cpp elapsed=14.29s
[2026-09-22 17:21:42] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-22 17:21:44] autostart default profile=fast
[2026-09-22 17:21:44] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-22 17:21:44] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-22 17:21:44] engine pid=631 engine=llama.cpp cpus=2
[2026-09-22 17:21:52] local agent ready engine=llama.cpp elapsed=7.73s
[2026-09-22 17:22:57] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-22 17:22:59] autostart default profile=fast
[2026-09-22 17:22:59] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-22 17:22:59] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-22 17:22:59] engine pid=570 engine=llama.cpp cpus=2
[2026-09-22 17:23:05] local agent ready engine=llama.cpp elapsed=6.36s
[2026-09-22 17:55:27] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-22 17:55:29] autostart default profile=fast
[2026-09-22 17:55:29] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-22 17:55:29] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-22 17:55:29] engine pid=502 engine=llama.cpp cpus=2
[2026-09-22 17:55:37] local agent ready engine=llama.cpp elapsed=8.06s
[2026-09-22 18:03:25] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-22 18:03:28] autostart default profile=fast
[2026-09-22 18:03:28] starting profile=fast engine=llama.cpp repo=unsloth/Qwen3-1.7B-GGUF
[2026-09-22 18:03:28] GGUF cache verified repo=unsloth/Qwen3-1.7B-GGUF file=/mnt/data/models/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q4_K_M.gguf size=1107409472
[2026-09-22 18:03:28] engine pid=466 engine=llama.cpp cpus=2
[2026-09-22 18:03:35] local agent ready engine=llama.cpp elapsed=7.87s
[2026-09-22 18:10:37] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-22 18:10:47] local agent ready engine=llama.cpp elapsed=7.18s
[2026-09-22 18:26:32] KV save before stop: saved=True tokens=26 bytes=839788
[2026-09-22 18:26:32] stopping proxy pid=499
[2026-09-22 18:26:32] stopping engine pid=497
[2026-09-22 18:29:10] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-22 18:33:58] local agent manager starting cpus=2 memoryGiB=14.9
[2026-09-22 18:38:29] local agent manager starting cpus=2 memoryGiB=14.9