Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
FINAL-Bench
/
Darwin-9B-MFP4
like
11
Follow
FINAL_Bench
147
Text Generation
Transformers
Safetensors
English
Korean
qwen3_5
image-text-to-text
darwin
mfp4
mixed-precision
nvfp4
quantization
blackwell
reasoning
conversational
modelopt
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
Darwin-9B-MFP4
11 GB
Ctrl+K
Ctrl+K
1 contributor
History:
5 commits
SeaWolf-AI
Enhance card: MFP4 technique, Darwin platform integration, hardware rationale
7da8a2b
verified
3 days ago
.gitattributes
Safe
1.57 kB
Initial upload: Darwin-9B-MFP4 (Mixed FP4) — 60% on GPQA dev20, +10pp vs BF16
3 days ago
README.md
6.81 kB
Enhance card: MFP4 technique, Darwin platform integration, hardware rationale
3 days ago
chat_template.jinja
Safe
7.76 kB
Initial upload: Darwin-9B-MFP4 (Mixed FP4) — 60% on GPQA dev20, +10pp vs BF16
3 days ago
config.json
8.05 kB
Initial upload: Darwin-9B-MFP4 (Mixed FP4) — 60% on GPQA dev20, +10pp vs BF16
3 days ago
generation_config.json
Safe
115 Bytes
Initial upload: Darwin-9B-MFP4 (Mixed FP4) — 60% on GPQA dev20, +10pp vs BF16
3 days ago
hf_quant_config.json
1.67 kB
Initial upload: Darwin-9B-MFP4 (Mixed FP4) — 60% on GPQA dev20, +10pp vs BF16
3 days ago
model.safetensors
11 GB
xet
Initial upload: Darwin-9B-MFP4 (Mixed FP4) — 60% on GPQA dev20, +10pp vs BF16
3 days ago
preprocessor_config.json
Safe
390 Bytes
Initial upload: Darwin-9B-MFP4 (Mixed FP4) — 60% on GPQA dev20, +10pp vs BF16
3 days ago
tokenizer.json
Safe
20 MB
xet
Initial upload: Darwin-9B-MFP4 (Mixed FP4) — 60% on GPQA dev20, +10pp vs BF16
3 days ago
tokenizer_config.json
Safe
1.1 kB
Initial upload: Darwin-9B-MFP4 (Mixed FP4) — 60% on GPQA dev20, +10pp vs BF16
3 days ago
