Johnny Everson
khronnuz
AI & ML interests
Code generation/tool usage
Recent Activity
updated a model about 8 hours ago
khronnuz/Ling-3.0-flash-exl3 published a model about 9 hours ago
khronnuz/Ling-3.0-flash-exl3 new activity about 18 hours ago
turboderp/Qwen3.8-Flash-Next-exl3:KV quantization sweep: 2K–128KOrganizations
None yet
KV quantization sweep: 2K–128K
👍🔥 8
3
#13 opened 16 days ago
by
khronnuz
4.05bpw thinking in other languages and/or gibberish
👀 1
5
#5 opened 24 days ago
by
khronnuz
reasoning content not split on Qwen3.8-Flash-Next EXL3 — thinking stays inline in content
3
#4 opened 25 days ago
by
khronnuz
Can we get a 6bit quant?
👍 3
1
#15 opened 28 days ago
by
khronnuz
Excessive CoT verbosity on simple, well-defined tasks
9
#5 opened about 1 month ago
by
desugar
mmproj and mtp files?
👀 6
7
#2 opened about 1 month ago
by
khronnuz
Chat template issue and ways to solve it
❤️👍 7
6
#42 opened about 1 month ago
by
Snol-std
Laguna S 2.1
#1 opened 2 months ago
by
khronnuz
Strong model. a bit slow. MTP?
10
#1 opened 3 months ago
by
khronnuz
Benchmarks?
👍 4
11
#2 opened 3 months ago
by
volodXYZ
Excellent long-context capabilities, but issue with output repetition
6
#1 opened 3 months ago
by
Kelheor
Loop :(
10
#3 opened 3 months ago
by
Ukro
Llama-cpp support has dropped.
2
#1 opened 3 months ago
by
khronnuz
Carnice V2 for Qwen 3.6 35B?
1
#3 opened 4 months ago
by
robbintt
This works with a quantsized version?
2
#4 opened 5 months ago
by
khronnuz
Does this work with quantsized version of 26B?
#3 opened 5 months ago
by
khronnuz
Broken template?
#1 opened 5 months ago
by
khronnuz
Getting stuck in thinking
🔥 2
29
#1 opened 6 months ago
by
khronnuz
Constantly getting stuck
2
#3 opened 6 months ago
by
khronnuz
Constantly getting stuck
2
#3 opened 6 months ago
by
khronnuz