Alan Givati
Qnibbles
·
AI & ML interests
None yet
Recent Activity
liked a model about 2 hours ago
unsloth/Qwen3.8-27B-NVFP4 liked a model 10 days ago
inclusionAI/Ling-3.0-flash liked a model 10 days ago
inclusionAI/LLaDA2.2-flashOrganizations
None yet
MoE backend config instructions
#16 opened 13 days ago
by
Qnibbles
Safetensors variant?
1
#1 opened 15 days ago
by
maglat
Does this support MTP?
#1 opened 18 days ago
by
Qnibbles
Still looping after update - details inside
👀 2
22
#10 opened 23 days ago
by
cbert33
FP8 quant
➕ 1
#15 opened 3 months ago
by
Qnibbles
Usage of preserve_thinking in OpenCode, etc
#2 opened 3 months ago
by
Qnibbles
Difference between models
1
#5 opened 3 months ago
by
Qnibbles
Base model no longer available?
#1 opened 3 months ago
by
Qnibbles
Possible config issue
#2 opened 4 months ago
by
Qnibbles
ValueError: Tokenizer class TokenizersBackend does not exist or is not currently imported
3
#1 opened 4 months ago
by
Qnibbles
Qwen3.5-122B-A10B version?
1
#20 opened 4 months ago
by
Qnibbles
Model accuracy
1
#12 opened 4 months ago
by
Qnibbles
Safetensors?
4
#2 opened 5 months ago
by
jeffbenson1979
Input tensor shape warnings
#2 opened 5 months ago
by
Qnibbles
Mixed MXFP4 and Q4
🔥 2
2
#1 opened 6 months ago
by
krampenschiesser
Please release a checkpoint for Qwen/Qwen3.5-122B-A10B
➕👍 4
3
#4 opened 6 months ago
by
Qnibbles
chat template is broken
11
#12 opened 6 months ago
by
grapevine-AI
Single RTX Pro 6000 users
4
#1 opened 6 months ago
by
lightenup
Request for NVFP4 version that will work with vLLM
2
#1 opened 6 months ago
by
Qnibbles