Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
mlx-community
/
LFM2-8B-A1B-3bit-MLX
like
1
Follow
MLX Community
7.21k
Text Generation
MLX
Safetensors
English
lfm2_moe
apple-silicon
liquidai
lfm2
Mixture of Experts
transformer
long-context
instruct
quantized
3bit
coding
conversational
custom_code
3-bit
License:
lfm1.0
Model card
Files
Files and versions
xet
Community
Use this model
main
LFM2-8B-A1B-3bit-MLX
4.18 GB
1 contributor
History:
8 commits
Susant-Achary
Update README.md
0b05ca1
verified
28 days ago
.gitattributes
Safe
1.52 kB
initial commit
28 days ago
README.md
4.35 kB
Update README.md
28 days ago
chat_template.jinja
Safe
1.3 kB
Add MLX 3-bit quantized weights (LFM2-8B-A1B)
28 days ago
config.json
6.42 kB
Add MLX 3-bit quantized weights (LFM2-8B-A1B)
28 days ago
generation_config.json
Safe
137 Bytes
Add MLX 3-bit quantized weights (LFM2-8B-A1B)
28 days ago
model.safetensors
4.17 GB
xet
Add MLX 3-bit quantized weights (LFM2-8B-A1B)
28 days ago
model.safetensors.index.json
43.3 kB
Add MLX 3-bit quantized weights (LFM2-8B-A1B)
28 days ago
special_tokens_map.json
Safe
434 Bytes
Add MLX 3-bit quantized weights (LFM2-8B-A1B)
28 days ago
tokenizer.json
Safe
4.73 MB
Add MLX 3-bit quantized weights (LFM2-8B-A1B)
28 days ago
tokenizer_config.json
Safe
91.9 kB
Add MLX 3-bit quantized weights (LFM2-8B-A1B)
28 days ago
