MLX Community · First MLX build 24 Apr 2026
deepseek-ai-DeepSeek-V4-Flash
MLX
A model, with 2 MLX builds, from 2-bit to fp16.
- Parameters
- — Not published
- Quantisation
- 2-bit deepseek-ai-DeepSeek-V4-Flash-2bit
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 0 This build, last 30 days
- Task
- —
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/deepseek-ai-DeepSeek-V4-Flash-2bitMLX builds
2 on mlx-community| deepseek-ai-DeepSeek-V4-Flash-2bit | 2-bit | — | — | 0 |
|---|---|---|---|---|
| deepseek-ai-DeepSeek-V4-Flash-fp16 | fp16 | — | — | 0 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.