Perfect parameters for coding !!! SHARE YOURS
π 5
1
#14 opened 19 days ago
by
Ukro
Qwen3.5-27B.Q8_0.gguf does not work!
#13 opened 19 days ago
by
beginor
Rys compatability/experiments?
π 1
#12 opened 21 days ago
by
Systox
How to suppress the CoT info from the output?
2
#11 opened 21 days ago
by
nailding1
AWQ 4-bit version of this Opus-Distilled-v2 model?
π 2
4
#10 opened 21 days ago
by
0xburakcelik
llama.cpp may crash
#9 opened 21 days ago
by
osabc
When Qwen/Qwen3.5-122B-A10B Opus 4.6 Reasoning Distilled????
#8 opened 25 days ago
by
Rubertigno
can't run in ollama 0.18.2
β 3
2
#7 opened 25 days ago
by
kuolung
Qwen3.5-27B.Q8_0.gguf got dummy output with llama.cpp
3
#6 opened 27 days ago
by
beginor
Stopping Execution
π 1
2
#5 opened 28 days ago
by
clackingjack
BF16 part 2 of 2?
π 2
2
#4 opened 30 days ago
by
flipplefozz
Interest in 3 bit version + CPU Optimization
#3 opened about 1 month ago
by
19440harry
Possible Image Mismatch in Model Card
#2 opened about 1 month ago
by
eborzone
when 35b a3b will come
ππ 4
6
#1 opened about 1 month ago
by
vanty120