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-AWQ
Like
0
Safetensors
gemma4
awq
4-bit precision
rdna4
gfx1201
rocm
sglang
quantized
thinking
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
gemma-4-31B-AWQ
19.2 GB
Ctrl+K
Ctrl+K
1 contributor
History:
4 commits
mattbucci
Fix chat_template: close model turn after tool_call + tool_response (agentic tool-call fix)
16c88ba
verified
4 months ago
.gitattributes
Safe
1.57 kB
Initial in-house AWQ build (calibration: balanced_thinking_vision, 0 scale flags)
5 months ago
README.md
Safe
3.17 kB
Initial in-house AWQ build (calibration: balanced_thinking_vision, 0 scale flags)
5 months ago
chat_template.jinja
Safe
17.3 kB
Fix chat_template: close model turn after tool_call + tool_response (agentic tool-call fix)
4 months ago
config.json
Safe
4.89 kB
Gemma 4 31B Dense AWQ (in-house BF16->GPTQ->AWQ, thinking+vision+video, 5/5 @ 256K)
4 months ago
generation_config.json
Safe
203 Bytes
Initial in-house AWQ build (calibration: balanced_thinking_vision, 0 scale flags)
5 months ago
model-00001-of-00010.safetensors
Safe
2.82 GB
xet
Initial in-house AWQ build (calibration: balanced_thinking_vision, 0 scale flags)
5 months ago
model-00002-of-00010.safetensors
Safe
2 GB
xet
Gemma 4 31B Dense AWQ (in-house BF16->GPTQ->AWQ, thinking+vision+video, 5/5 @ 256K)
4 months ago
model-00003-of-00010.safetensors
Safe
2 GB
xet
Gemma 4 31B Dense AWQ (in-house BF16->GPTQ->AWQ, thinking+vision+video, 5/5 @ 256K)
4 months ago
model-00004-of-00010.safetensors
Safe
2.01 GB
xet
Gemma 4 31B Dense AWQ (in-house BF16->GPTQ->AWQ, thinking+vision+video, 5/5 @ 256K)
4 months ago
model-00005-of-00010.safetensors
Safe
1.98 GB
xet
Gemma 4 31B Dense AWQ (in-house BF16->GPTQ->AWQ, thinking+vision+video, 5/5 @ 256K)
4 months ago
model-00006-of-00010.safetensors
Safe
1.96 GB
xet
Gemma 4 31B Dense AWQ (in-house BF16->GPTQ->AWQ, thinking+vision+video, 5/5 @ 256K)
4 months ago
model-00007-of-00010.safetensors
Safe
1.96 GB
xet
Gemma 4 31B Dense AWQ (in-house BF16->GPTQ->AWQ, thinking+vision+video, 5/5 @ 256K)
4 months ago
model-00008-of-00010.safetensors
Safe
2.01 GB
xet
Gemma 4 31B Dense AWQ (in-house BF16->GPTQ->AWQ, thinking+vision+video, 5/5 @ 256K)
4 months ago
model-00009-of-00010.safetensors
Safe
2 GB
xet
Gemma 4 31B Dense AWQ (in-house BF16->GPTQ->AWQ, thinking+vision+video, 5/5 @ 256K)
4 months ago
model-00010-of-00010.safetensors
Safe
443 MB
xet
Gemma 4 31B Dense AWQ (in-house BF16->GPTQ->AWQ, thinking+vision+video, 5/5 @ 256K)
4 months ago
model.safetensors.index.json
Safe
200 kB
Gemma 4 31B Dense AWQ (in-house BF16->GPTQ->AWQ, thinking+vision+video, 5/5 @ 256K)
4 months ago
processor_config.json
Safe
1.69 kB
Initial in-house AWQ build (calibration: balanced_thinking_vision, 0 scale flags)
5 months ago
tokenizer.json
Safe
32.2 MB
xet
Initial in-house AWQ build (calibration: balanced_thinking_vision, 0 scale flags)
5 months ago
tokenizer_config.json
Safe
19.6 kB
Initial in-house AWQ build (calibration: balanced_thinking_vision, 0 scale flags)
5 months ago