Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
JasmineBBB
/
Kimi-Linear-48B-A3B-Instruct-bnb-4bit
like
1
Text Generation
Safetensors
kimi_linear
sglang
vllm
conversational
custom_code
4-bit precision
bitsandbytes
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
Kimi-Linear-48B-A3B-Instruct BNB - FP4
Model Details
Kimi-Linear-48B-A3B-Instruct BNB - FP4
Model Details
Quantization Method:
BNB
Bits:
4
Compute Dtype:
bfloat16
Downloads last month
114
Safetensors
Model size
49B params
Tensor type
F32
路
F16
路
U8
路
Chat template
Files info
Inference Providers
NEW
Text Generation
This model isn't deployed by any Inference Provider.
馃檵
Ask for provider support
Model tree for
JasmineBBB/Kimi-Linear-48B-A3B-Instruct-bnb-4bit
Base model
moonshotai/Kimi-Linear-48B-A3B-Instruct
Quantized
(
24
)
this model
