Can deepseek coder 6.7b base run on the Mac M4 Max 128GB?
Yes. At 8K context the best fit is F16, using about 17.0 GB of the 96.0 GB usable on the Mac M4 Max 128GB. Estimated speed ceiling: ~41 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | Max tok/s (est., 8K) |
|---|---|---|---|
| 2-bit (Q2_K) • | 4.8 GB Fits | 6.8 GB Fits | 215 |
| 3-bit (Q3_K_M) • | 5.5 GB Fits | 7.5 GB Fits | 165 |
| 4-bit (Q4_K_M) • | 6.3 GB Fits | 8.3 GB Fits | 134 |
| 5-bit (Q5_K_M) • | 6.9 GB Fits | 8.9 GB Fits | 114 |
| 6-bit (Q6_K) • | 7.6 GB Fits | 9.6 GB Fits | 99 |
| 8-bit (Q8_0) • | 9.1 GB Fits | 11.1 GB Fits | 76 |
| 16-bit (F16/BF16) | 15.0 GB Fits | 17.0 GB Fits | 41 |
• real GGUF file size from bartowski/deepseek-coder-6.7B-kexer-GGUF. Speed is a bandwidth ceiling (546 GB/s), not a benchmark. Methodology.
More
deepseek coder 6.7b base on every GPU and Mac · Every model that runs on the Mac M4 Max 128GB · Apple Silicon guide · Try other settings in the calculator
Data: Hugging Face Hub (deepseek-ai/deepseek-coder-6.7b-base), Apple specs. Data as of 2026-11-17.