Seed-Coder-8B-Reasoning-bf16-mlx-4Bit
mlx-community/Seed-Coder-8B-Reasoning-bf16-mlx-4Bit
Text generation · transformers
4-bit Open on Hugging Face
Parameters
8.3B
Weights (est.)
≈ 4.6 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/Seed-Coder-8B-Reasoning-bf16-mlx-4Bit --prompt "Hello"
Details
- Base model
- ByteDance-Seed/Seed-Coder-8B-Reasoning-bf16 (quantized)
- Vendor
- ByteDance-Seed
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 42 in the last 30 days · 492 all time · 0 likes
- Published
- 2025-07-18 · updated 2025-07-18 (1y ago)
- Tags
- llama
Other MLX builds of ByteDance-Seed/Seed-Coder-8B-Reasoning-bf16
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Seed-Coder-8B-Reasoning-bf16-mlx-4Bit (this one) | 4-bit | ≈ 4.6 GB | 8 GB+ | 42 |
| Seed-Coder-8B-Reasoning-bf16-mlx-8Bit | 8-bit | ≈ 8.8 GB | 16 GB+ | 50 |
| Seed-Coder-8B-Reasoning-bf16-mlx-fp16 | bf16 | ≈ 16.5 GB | 24 GB+ | 30 |