Hugging Face's logo

ReadyArt
/
Mistral-Small-3.1-DRAFT-0.5B-AWQ

Text Generation
Transformers
Safetensors
qwen2
qwen
qwen2.5
mistral
mistral-small
mistral-small-3.1
conversational
text-generation-inference
4-bit precision
awq
Model card Files
xet
Community

Mistral Small 3.1 DRAFT 0.5B

Released by alamios

Quant by FrenzyBiscuit

FrenzyBiscuit

AWQ Details

  • Model was quantized down to INT4 using GEMM Kernels.
  • Zero point quantization
  • Group size of 64
Downloads last month
6
Safetensors
Model size
286M params
Tensor type
I32
·
BF16
·
F16
·
Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ReadyArt/Mistral-Small-3.1-DRAFT-0.5B-AWQ

Base model

Qwen/Qwen2.5-0.5B
Finetuned
alamios/Qwenstral-Small-3.1-0.5B
Finetuned
alamios/Mistral-Small-3.1-DRAFT-0.5B
Quantized
(16)
this model

Dataset used to train ReadyArt/Mistral-Small-3.1-DRAFT-0.5B-AWQ

Collection including ReadyArt/Mistral-Small-3.1-DRAFT-0.5B-AWQ