Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
majentik
/
Mistral-Small-4-119B-RotorQuant-MLX-2bit
like
0
Text Generation
MLX
Safetensors
English
mistral3
rotorquant
kv-cache-quantization
mistral
Mixture of Experts
sparse-moe
multimodal
quantized
2-bit
apple-silicon
256k-context
thinking
conversational
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Use this model
ba08f9e
Mistral-Small-4-119B-RotorQuant-MLX-2bit
38.3 GB
Ctrl+K
Ctrl+K
1 contributor
History:
3 commits
majentik
Add MLX quantized model weights
ba08f9e
verified
11 days ago
.gitattributes
Safe
1.89 kB
Add MLX quantized model weights
11 days ago
README.md
Safe
3.7 kB
Add model card (weights pending mlx_lm mistral3 architecture support)
11 days ago
chat_template.jinja
Safe
5.92 kB
Add MLX quantized model weights
11 days ago
config.json
Safe
9.25 kB
Add MLX quantized model weights
11 days ago
consolidated.safetensors.index.json
Safe
3.62 MB
Add MLX quantized model weights
11 days ago
generation_config.json
Safe
132 Bytes
Add MLX quantized model weights
11 days ago
model-00001-of-00014.safetensors
Safe
3.58 GB
xet
Add MLX quantized model weights
11 days ago
model-00002-of-00014.safetensors
Safe
2.8 GB
xet
Add MLX quantized model weights
11 days ago
model-00003-of-00014.safetensors
Safe
2.72 GB
xet
Add MLX quantized model weights
11 days ago
model-00004-of-00014.safetensors
2.74 GB
xet
Add MLX quantized model weights
11 days ago
model-00005-of-00014.safetensors
Safe
2.74 GB
xet
Add MLX quantized model weights
11 days ago
model-00006-of-00014.safetensors
Safe
2.72 GB
xet
Add MLX quantized model weights
11 days ago
model-00007-of-00014.safetensors
2.74 GB
xet
Add MLX quantized model weights
11 days ago
model-00008-of-00014.safetensors
2.74 GB
xet
Add MLX quantized model weights
11 days ago
model-00009-of-00014.safetensors
Safe
2.72 GB
xet
Add MLX quantized model weights
11 days ago
model-00010-of-00014.safetensors
2.74 GB
xet
Add MLX quantized model weights
11 days ago
model-00011-of-00014.safetensors
2.74 GB
xet
Add MLX quantized model weights
11 days ago
model-00012-of-00014.safetensors
Safe
2.72 GB
xet
Add MLX quantized model weights
11 days ago
model-00013-of-00014.safetensors
Safe
2.74 GB
xet
Add MLX quantized model weights
11 days ago
model-00014-of-00014.safetensors
Safe
1.87 GB
xet
Add MLX quantized model weights
11 days ago
model.safetensors.index.json
Safe
182 kB
Add MLX quantized model weights
11 days ago
params.json
Safe
1.51 kB
Add MLX quantized model weights
11 days ago
processor_config.json
Safe
701 Bytes
Add MLX quantized model weights
11 days ago
tekken.json
Safe
16.3 MB
xet
Add MLX quantized model weights
11 days ago
tokenizer.json
Safe
17.1 MB
xet
Add MLX quantized model weights
11 days ago
tokenizer_config.json
Safe
21.2 kB
Add MLX quantized model weights
11 days ago
