Commit History
-
Upload 2 files
Verified signaturefb22ecb -
Upload Qwen3.8-27B-mmproj-F16.gguf
Verified signature877e9f5 -
Upload Qwen3.8-27B-Q4_K_M.gguf
Verified signature334fc67
-
Upload gemma-4-12B-it-qat-q4_0-assistant-Q4_0.gguf
Verified signature2eb1f63 -
Upload 2 files
Verified signature57db305
-
Delete mmproj-gemma-4-12b-it-qat-q4_0.gguf
Verified signature52281ae -
Upload gemma-4-12b-it-qat-q4_0-it-mmproj.gguf
Verified signature376bede -
Gemma 4 QAT assistant/draft models (12B/26Ba4B, 31B)
Verified signature03adbd4 -
Upload gemma-4-31B_q4_0-it.gguf
Verified signature0ab0b8e -
Gemma 4 QAT: 12B, 26B, 31B mmproj
Verified signature213fed1
-
Gemma 4 26B-A4B
Verified signature5f9a741 -
Gemma 4 31B
Verified signaturea762267 -
Gemma 4 E2B and E4B
Verified signature3f97149
-
Qwen 3.6 35B A3B
Verified signatureee27125
-
Qwen 3.5 mmprojs (via unsloth)
Verified signaturefca96b6
-
Qwen 3.5 35B 35B-A3B via Unsloth
Verified signature85e26cd -
Qwen 3.5 27B via Unsloth
Verified signatureac7a855 -
Qwen 3.5 0.8B, 2B, 4B, 9B via Unsloth
Verified signature996229d
-
Upload sharded TinyStories for testing sharded model DL
Verified signature4e5227d -
Upload sharded DeepSeek-R1 for testing sharded model DLs.
Verified signatured5fb402
-
Upload gpt-oss-120b-mxfp4-00001-of-00003.gguf
Verified signaturef75376e -
Upload 2 files
Verified signature8f4d5d1
-
Upload HuggingFaceTB_SmolLM3-3B-Q4_0.gguf
Verified signatureBartowski's q4 with template from: https://huggingface.co/ggml-org/SmolLM3-3B-GGUF. HF staff manually updated the template at ggml-org after release; there's an extra [:] on some arrays on the original template. That used to work, but, now llama.cpp is refusing to inference SmolLM3 with an error about a vector at row X column Y. I believe using this file will fix that.e14f222
-
Upload gpt-oss-20b-mxfp4.gguf
Verified signature00524bb
-
Upload 4 files
Verified signaturedbbd9e7
-
Upload deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_0.gguf
Verified signature88eddaf -
Upload DeepSeek-R1-Distill-Qwen-1.5B-Q4_0.gguf
Verified signature5b28cc3 -
Upload Llama-3.2-1B-Instruct-Q4_0.gguf
Verified signature8f6a590 -
Upload HuggingFaceTB_SmolLM3-3B-Q4_0.gguf
Verified signature4af2dd3 -
Delete Phi-3.5-mini-instruct-IQ4_XS.gguf
Verified signature2905001 -
Upload microsoft_Phi-4-mini-instruct-Q4_0.gguf
Verified signature459ecff
-
Upload SmolLM3-Q4_K_M.gguf
Verified signaturevia gguf org's repo01f6122
-
Upload deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_K_M.gguf
Verified signaturevia bartowskic3e4555
-
Rename mmproj-google_gemma-3-27b-it-f32 (1).gguf to google_gemma-3-27b-it-f32.mmproj.gguf
Verified signature03b7dbf -
Upload mmproj-google_gemma-3-27b-it-f32 (1).gguf
Verified signaturea54163a -
Upload google_gemma-3-27b-it-Q4_K_M.gguf
Verified signature22ec137
-
Rename mmproj-google_gemma-3-12b-it-f16.gguf to google_gemma-3-12b-it-f16.mmproj.gguf
Verified signature778346c -
Upload google_gemma-13-12b-it and mmproj
Verified signature3a08885
-
Upload microsoft_Phi-4-mini-instruct-Q4_K_M.gguf
Verified signatureacf95e7
-
Upload DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf
Verified signaturefa5d578
-
Upload Llama-3.2-1B-Instruct-Q4_K_M.gguf
Verified signature3abf94e -
Delete tinymistral-248m-sft-v4.q2_k.gguf
Verified signaturef6a4c4b -
Delete stablelm-zephyr-3b.Q4_K_M.gguf
Verified signaturedabb7ba -
Delete dolphin-2.9-llama3-8b-1m-Q4_K_M.gguf
Verified signature7856cc8 -
Delete Phi-3.1-mini-128k-instruct-Q4_K_M.gguf
Verified signature8838517
-
Upload Phi-3.5-mini-instruct-IQ4_XS.gguf
Verified signaturevia @bartowskic8c745c
-
Upload Meta-Llama-3.1-8B-Instruct-Q4_K_M-take2.gguf
Verified signatureFrom https://huggingface.co/lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF/tree/main9e05861
-
Delete Phi-3-mini-128k-instruct.Q4_K_M.gguf
Verified signature36b3f0c -
Upload Phi-3.1-mini-128k-instruct-Q4_K_M.gguf
Verified signatureb654ceb
-
Upload DistilGPT2-TinyStories.IQ3_M.gguf
Verified signatureMistral Tiny crashes in ggml assert in latest llama.cpps. This is the smallest gguf I could find that is valid. The recommend demo GGUF creation can't provide output.e6f6e6a