Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
mattbucci
/
gemma-4-31B-it-AutoRound-AWQ
like
0
Safetensors
gemma4
awq
4-bit precision
rdna4
gfx1201
rocm
sglang
quantized
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
gemma-4-31B-it-AutoRound-AWQ
19.2 GB
Ctrl+K
Ctrl+K
1 contributor
History:
11 commits
mattbucci
docs: note red-circle vision regression (upstream Gemma 4 limit, not calibration)
364b295
verified
3 months ago
.gitattributes
Safe
1.57 kB
Gemma 4 31B AWQ: AutoRound GPTQ→AWQ converted, full dequant→requant for symmetric scales
4 months ago
README.md
2.53 kB
docs: note red-circle vision regression (upstream Gemma 4 limit, not calibration)
3 months ago
chat_template.jinja
Safe
12 kB
Gemma 4 31B AWQ: AutoRound GPTQ→AWQ converted, full dequant→requant for symmetric scales
4 months ago
config.json
4.95 kB
add quantization_config.ignore=['lm_head', 're:vision_tower.*'] (downstream audit fix)
3 months ago
generation_config.json
Safe
203 Bytes
Gemma 4 31B AWQ: AutoRound GPTQ→AWQ converted, full dequant→requant for symmetric scales
4 months ago
model-00001-of-00010.safetensors
2.15 GB
xet
Gemma 4 31B AWQ: AutoRound GPTQ→AWQ converted, full dequant→requant for symmetric scales
4 months ago
model-00002-of-00010.safetensors
Safe
2.15 GB
xet
Gemma 4 31B AWQ: AutoRound GPTQ→AWQ converted, full dequant→requant for symmetric scales
4 months ago
model-00003-of-00010.safetensors
Safe
2.11 GB
xet
Gemma 4 31B AWQ: AutoRound GPTQ→AWQ converted, full dequant→requant for symmetric scales
4 months ago
model-00004-of-00010.safetensors
Safe
2.14 GB
xet
Gemma 4 31B AWQ: AutoRound GPTQ→AWQ converted, full dequant→requant for symmetric scales
4 months ago
model-00005-of-00010.safetensors
Safe
2.14 GB
xet
Gemma 4 31B AWQ: AutoRound GPTQ→AWQ converted, full dequant→requant for symmetric scales
4 months ago
model-00006-of-00010.safetensors
Safe
2.11 GB
xet
Gemma 4 31B AWQ: AutoRound GPTQ→AWQ converted, full dequant→requant for symmetric scales
4 months ago
model-00007-of-00010.safetensors
Safe
2.15 GB
xet
Gemma 4 31B AWQ: AutoRound GPTQ→AWQ converted, full dequant→requant for symmetric scales
4 months ago
model-00008-of-00010.safetensors
Safe
272 MB
xet
Gemma 4 31B AWQ: AutoRound GPTQ→AWQ converted, full dequant→requant for symmetric scales
4 months ago
model-00009-of-00010.safetensors
Safe
2.82 GB
xet
Gemma 4 31B AWQ: AutoRound GPTQ→AWQ converted, full dequant→requant for symmetric scales
4 months ago
model-00010-of-00010.safetensors
Safe
10.9 kB
xet
Gemma 4 31B AWQ: AutoRound GPTQ→AWQ converted, full dequant→requant for symmetric scales
4 months ago
model-vision.safetensors
Safe
1.15 GB
xet
Add vision weights from BF16 base model (model-vision.safetensors)
4 months ago
model.safetensors.index.json
Safe
197 kB
Add vision weights from BF16 base model (model.safetensors.index.json)
4 months ago
preprocessor_config.json
Safe
403 Bytes
Gemma 4 31B AWQ: AutoRound GPTQ→AWQ converted, full dequant→requant for symmetric scales
4 months ago
processor_config.json
Safe
1.69 kB
Gemma 4 31B AWQ: AutoRound GPTQ→AWQ converted, full dequant→requant for symmetric scales
4 months ago
quantization_config.json
Safe
241 Bytes
Gemma 4 31B AWQ: AutoRound GPTQ→AWQ converted, full dequant→requant for symmetric scales
4 months ago
tokenizer.json
Safe
32.2 MB
xet
Gemma 4 31B AWQ: AutoRound GPTQ→AWQ converted, full dequant→requant for symmetric scales
4 months ago
tokenizer_config.json
Safe
2.69 kB
Gemma 4 31B AWQ: AutoRound GPTQ→AWQ converted, full dequant→requant for symmetric scales
4 months ago