OsaurusAI
/

Gemma-4-26B-A4B-it-JANG_4M

mixed-precision

Mixture of Experts

Model card Files Files and versions

Gemma-4-26B-A4B-it-JANG_4M

Ctrl+K

Ctrl+K

1 contributor

History: 5 commits

Osaurus-AI's picture

capabilities: stamp reasoning/tool parser + cache_type for vmlx CapabilityDetector Tier-1

af3c1c0 verified 6 days ago

.gitattributes

1.57 kB
Add Gemma 4 26B-A4B JANG_4M quantized model 19 days ago
README.md

5.58 kB
Add MMLU benchmark results 19 days ago
chat_template.jinja

12 kB
Add Gemma 4 26B-A4B JANG_4M quantized model 19 days ago
config.json

3.88 kB
Add Gemma 4 26B-A4B JANG_4M quantized model 19 days ago
generation_config.json

208 Bytes
Add Gemma 4 26B-A4B JANG_4M quantized model 19 days ago
jang_config.json

1.04 kB
capabilities: stamp reasoning/tool parser + cache_type for vmlx CapabilityDetector Tier-1 6 days ago
model-00001-of-00004.safetensors

5.25 GB
xet

Add Gemma 4 26B-A4B JANG_4M quantized model 19 days ago
model-00002-of-00004.safetensors

5.32 GB
xet

Add Gemma 4 26B-A4B JANG_4M quantized model 19 days ago
model-00003-of-00004.safetensors

5.36 GB
xet

Add Gemma 4 26B-A4B JANG_4M quantized model 19 days ago
model-00004-of-00004.safetensors

231 MB
xet

Add Gemma 4 26B-A4B JANG_4M quantized model 19 days ago
model.safetensors.index.json

170 kB
Add Gemma 4 26B-A4B JANG_4M quantized model 19 days ago
processor_config.json

1.69 kB
Add Gemma 4 26B-A4B JANG_4M quantized model 19 days ago
tokenizer.json

32.2 MB
xet

Add Gemma 4 26B-A4B JANG_4M quantized model 19 days ago
tokenizer_config.json

2.07 kB
Add Gemma 4 26B-A4B JANG_4M quantized model 19 days ago