Downloads · 30 days
33
2% of all-time downloads
Deepseek-V4-Flash-oQ8-mtp
mkreynolds/Deepseek-V4-Flash-oQ8-mtp
Deepseek-V4-Flash-oQ8-mtp is a machine learning model from mkreynolds. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx.
This is an 8-bit mixed-precision quantization of Deepseek V4 Flash, using oQ (oMLX v0.5.1). This quant should in theory be lossless, due to Deepseek V4 Flash's native FP4/FP8 architecture. Fits within 192GB of unified…
All-time downloads
1.5K
Public
Parameters
291B
159 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors159 GB · 100%
Parameter types
How the weights are stored.
U32291B · 100%
Base models
Model card
From the Hugging Face model README
Deepseek-V4-Flash-oQ8-mtp
This is an 8-bit mixed-precision quantization of Deepseek V4 Flash, using oQ (oMLX v0.5.1). This quant should in theory be lossless, due to Deepseek V4 Flash's native FP4/FP8 architecture. Fits within 192GB of unified memory. MTP weights are preserved (use oMLX Lightning MTP).
I run this quant every day on an oMLX server for use with Openclaw. It performs well at multi-turn tool calling and coding tasks (just make sure to set blockstreamingdefault to "on" in Openclaw or else multi-turn tool calling will fail).
oMLX's highly efficient caching makes this version, in my experience, signficantly faster than ds4.c. The MLX architecture and MTP also lead to slight speed gains in prompt processing and decode.
Quantization details
- Model type: deepseek_v4
- Bits: 8
- Group size: 64
- Format: MLX safetensors
- Library
- mlx
- Type
- deepseek_v4
- Created
- Jul 18, 2026
- Updated
- Jul 18, 2026