Loc Huynh
JC1DA
AI & ML interests
Model optimization
Organizations
None yet
New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF 2 months ago
VERSION / QUANTS : [Sharing] INT4-INT8-Mixed version for dual 3090 users
👍❤️ 1
2
#56 opened 2 months ago
by
JC1DA
New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF 2 months ago
Reasoning Modes Work Well - Distinctly Different Thoughts Per Setting
🧠❤️ 3
7
#11 opened 2 months ago
by
dilletante
KV cache / loop
9
#3 opened 2 months ago
by
LastWardian
Loop occurred after like 10M tokens :)
5
#1 opened 2 months ago
by
JC1DA
SUPER Pelicans - in both Thinking and Instruct ,
😎 2
3
#6 opened 2 months ago
by
DavidAU
New activity in JC1DA/Qwen3.8-27B-DavidAU-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-INT4-W4A16 3 months ago
It would be even better if it had MTP.
2
#1 opened 3 months ago
by
markxixihaha
Sharing W4A16 model for 3090 users :)
👍 1
#2 opened 3 months ago
by
JC1DA
New activity in DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU 3 months ago
VERSION: Sharing W4A16 model for 3090 users
❤️👍 4
1
#17 opened 3 months ago
by
JC1DA
Access request so I can quantize it for oMLX
4
#14 opened 3 months ago
by
thgfnbv
Heretic/uncensored model in the future + vLLM RTX Pro 4500 start up variables
❤️ 1
4
#1 opened 3 months ago
by
Gabt123
FP16 safetensor models?
🔥 2
4
#10 opened 3 months ago
by
JC1DA
Is MTP supported?
#1 opened 4 months ago
by
JC1DA
KeyError: 'layers.0.ffn.experts.w13_qweight' when running on A100 GPU
2
#1 opened 4 months ago
by
JC1DA
New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 4 months ago
any plan to release the full precision model?
🔥👍 5
29
#3 opened 4 months ago
by
electroglyph
NVFP4/FP4 or INT4 quant?
❤️ 1
1
#2 opened 4 months ago
by
jc2375
Hi! is it still uploading? I have been waiting a while :D
2
#1 opened 5 months ago
by
rattl
Empty repo?
1
#1 opened 5 months ago
by
JC1DA
Got "!!!!!!!!!!!!!!!!!!" outputs
1
#1 opened 5 months ago
by
JC1DA
Gemma 4:124b
👍🚀 91
18
#1 opened 6 months ago
by
seamon67
Can I deploy it with sglang at my 8*4090 ubuntu sever?
10
#1 opened 7 months ago
by
marshal007