BuiDoan
BuiDoan
AI & ML interests
None yet
Recent Activity
liked a model 1 day ago
unsloth/Qwen3.6-27B-NVFP4 liked a model 1 day ago
mlx-community/Qwen3.6-27B-OptiQ-4bit liked a model 1 day ago
tencent/Hy3Organizations
IDEA: Bitnet 1.58 (a4.8) version in future variants would be so incredible!
❤️ 3
3
#10 opened 5 days ago
by
apiarium
Avg Draft acceptance rate: 0.0%
2
#1 opened about 2 months ago
by
BuiDoan
RuntimeError: expected mat1 and mat2 to have the same dtype, but got: float != c10::Half
3
#10 opened 2 months ago
by
mancub
Request for 4-bit Quantization
👍 1
#1 opened about 2 months ago
by
BuiDoan
Error compressed tensor sglang
➕ 7
3
#1 opened 3 months ago
by
amartinOnepoint
Quantization request
❤️ 1
#1 opened 2 months ago
by
BuiDoan
New activity in Sociopacific/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GPTQ-Int4 2 months ago
Anyone got experience with it?
#1 opened 2 months ago
by
BuiDoan
Avg Draft acceptance rate is low.
17
#2 opened 3 months ago
by
fouvy
Any reason no more 35b-a3b model release?
3
#4 opened 3 months ago
by
prunusis
Architectural Comparison: Qwen3.5-35B-A3B vs. Qwen3.6-35B-A3B
🔥 21
1
#12 opened 3 months ago
by
BuiDoan
MTP Speculation
👍 1
7
#11 opened 3 months ago
by
memtalow
Custom tokenizer
1
#1 opened 3 months ago
by
BuiDoan
AWQ 4-bit version of this Opus-Distilled-v2 model?
👍 2
4
#10 opened 4 months ago
by
celikburak
Unable to run (vllm/sglang)
8
#1 opened 4 months ago
by
nfunctor
Inquiry About Unsloth Dynamic 1.8-bit Qwen3-Coder-Next-UD-TQ1_0.gguf for vLLM Deployment
1
#6 opened 5 months ago
by
BuiDoan
Can I run this with 36gb VRAM+ 192gb ram
10
#1 opened 6 months ago
by
nimishchaudhari
vLLM compatible
#1 opened 7 months ago
by
BuiDoan
Loading Mistral Models in vLLM
1
#2 opened 7 months ago
by
BuiDoan
AWQ Quantization?
1
#7 opened 8 months ago
by
hoemwmt
Seeking User Experiences and Feedback
2
#2 opened 8 months ago
by
BuiDoan