DeepSeek-V4-Flash-oQ2e-mtp
This model was quantized using oQ (oMLX v0.5.2) mixed-precision quantization.
MMLU 500
336 / 500 correct · 67.2%
HUMANEVAL 148
148 / 164 correct · 90.2%
Quantization details
- Model type: deepseek_v4
- Bits: 2
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 655
Model size
29B params
Tensor type
BF16
·
U32 ·
F32 ·
U8 ·
I32 ·
Hardware compatibility
Log In to add your hardware
2-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support