Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
andrevp
/
Nanbeige4.1-3B-MLX-8bit
like
0
Text Generation
MLX
Safetensors
English
Chinese
llama
llm
nanbeige
quantized
8bit
reasoning
tool-calling
apple-silicon
conversational
8-bit precision
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Use this model
main
Nanbeige4.1-3B-MLX-8bit
4.2 GB
Ctrl+K
Ctrl+K
1 contributor
History:
4 commits
andrevp
Add extended thinking behavior documentation and workarounds
8a37d57
verified
2 months ago
.gitattributes
Safe
1.57 kB
Upload Nanbeige4.1-3B converted to MLX format (8-bit quantized)
2 months ago
README.md
13.1 kB
Add extended thinking behavior documentation and workarounds
2 months ago
added_tokens.json
Safe
174 Bytes
Upload Nanbeige4.1-3B converted to MLX format (8-bit quantized)
2 months ago
chat_template.jinja
Safe
5.53 kB
Upload Nanbeige4.1-3B converted to MLX format (8-bit quantized)
2 months ago
config.json
1.05 kB
Upload Nanbeige4.1-3B converted to MLX format (8-bit quantized)
2 months ago
generation_config.json
Safe
142 Bytes
Upload Nanbeige4.1-3B converted to MLX format (8-bit quantized)
2 months ago
model.safetensors
4.18 GB
xet
Upload Nanbeige4.1-3B converted to MLX format (8-bit quantized)
2 months ago
model.safetensors.index.json
52.4 kB
Upload Nanbeige4.1-3B converted to MLX format (8-bit quantized)
2 months ago
special_tokens_map.json
Safe
623 Bytes
Upload Nanbeige4.1-3B converted to MLX format (8-bit quantized)
2 months ago
tokenizer.json
Safe
18.5 MB
xet
Upload Nanbeige4.1-3B converted to MLX format (8-bit quantized)
2 months ago
tokenizer.model
Safe
2.78 MB
xet
Upload Nanbeige4.1-3B converted to MLX format (8-bit quantized)
2 months ago
tokenizer_config.json
Safe
2.31 kB
Upload Nanbeige4.1-3B converted to MLX format (8-bit quantized)
2 months ago
tokenizer_config_search.json
Safe
2.73 kB
Upload Nanbeige4.1-3B converted to MLX format (8-bit quantized)
2 months ago