4-bit Open on Hugging Face
Parameters
6.9B
Weights (est.)
≈ 3.9 GB
Mac memory (est.)
8 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/DeepSeek-Prover-V2-7B-4bit --prompt "Hello"
Details
- Base model
- deepseek-ai/DeepSeek-Prover-V2-7B (quantized)
- Vendor
- DeepSeek
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- —
- Downloads
- 179 in the last 30 days · 7.0K all time · 4 likes
- Published
- 2025-05-01 · updated 2025-05-01 (1y ago)
- Tags
- llama
Other MLX builds of deepseek-ai/DeepSeek-Prover-V2-7B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| DeepSeek-Prover-V2-7B-4bit (this one) | 4-bit | ≈ 3.9 GB | 8 GB+ | 179 |
| DeepSeek-Prover-V2-7B-8bit | 8-bit | ≈ 7.3 GB | 16 GB+ | 53 |
| DeepSeek-Prover-V2-7B-bf16 | bf16 | ≈ 13.8 GB | 24 GB+ | 55 |