Hugging Face's logo

gn00029914
/
F2LLM-v2-14B-oQ8-fp16

Feature Extraction
MLX
Safetensors
qwen3
oq
quantized
8-bit precision
Model card Files
xet
 Community

F2LLM-v2-14B-oQ8-fp16

This model was quantized using oQ (oMLX v0.3.8) mixed-precision quantization.

Quantization details

  • Model type: qwen3
  • Bits: 8
  • Group size: 64
  • Format: MLX safetensors
Downloads last month
25
Safetensors
Model size
14B params
Tensor type
U32
·
F16
·
MLX
Hardware compatibility
Log In to add your hardware

8-bit

Inference Providers NEW
Feature Extraction
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for gn00029914/F2LLM-v2-14B-oQ8-fp16

Base model

Qwen/Qwen3-14B-Base
Finetuned
Qwen/Qwen3-14B
Finetuned
codefuse-ai/F2LLM-v2-14B-Preview
Finetuned
codefuse-ai/F2LLM-v2-14B
Quantized
(3)
this model

Dataset used to train gn00029914/F2LLM-v2-14B-oQ8-fp16