John
koifish12
·
AI & ML interests
None yet
Recent Activity
new activity 6 days ago
unsloth/Qwen3.6-35B-A3B-MTP-GGUF:Fast! new activity 8 days ago
unsloth/Qwen3.6-35B-A3B-NVFP4:Vllm - Out of Memory Error new activity 9 days ago
z-lab/Qwen3.5-35B-A3B-PARO:can you guys do the 3.6 version?Organizations
None yet
Vllm - Out of Memory Error
4
#1 opened 16 days ago
by
H-J-D
can you guys do the 3.6 version?
#1 opened 9 days ago
by
koifish12
could you do a 4bit version?
🤝 1
2
#1 opened 16 days ago
by
koifish12
would this work with mtp?
1
#1 opened 15 days ago
by
koifish12
thanks for the great work
13
#1 opened about 1 month ago
by
koifish12
model looping during coding
#2 opened about 1 month ago
by
koifish12
could you create a 8bit mlx please?
#1 opened 2 months ago
by
koifish12
can you guys do qwen3.5 35b a3b and also the 27b variant?
#5 opened 2 months ago
by
koifish12
question about mxfp4
2
#3 opened 4 months ago
by
koifish12
Please update llama.cpp to see improved performance!
🚀 4
4
#7 opened 5 months ago
by
danielhanchen
how would you run this with llamacpp?
1
#1 opened 5 months ago
by
koifish12
can we also get the quants for the smaller qwen3 coder and glm 4.5 air reaps?
#2 opened 7 months ago
by
koifish12
Why not experiment?
👍 1
3
#1 opened 7 months ago
by
Dampfinchen
Qwen3-30B-A3B-Instruct-2507-UD-Q2_K_XL.gguf output garbled
1
#8 opened 8 months ago
by
CalvinZero
Streaming question
1
#18 opened 7 months ago
by
koifish12