Can deepseek coder 1.3b instruct run on the Mac M4 Pro 24GB?
Yes. At 8K context the best fit is F16, using about 4.5 GB of the 16.1 GB usable on the Mac M4 Pro 24GB. Estimated speed ceiling: ~101 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | Max tok/s (est., 8K) |
|---|---|---|---|
| 2-bit (Q2_K) • | 1.8 GB Fits | 2.5 GB Fits | 432 |
| 3-bit (Q3_K_M) • | 1.9 GB Fits | 2.6 GB Fits | 387 |
| 4-bit (Q4_K_M) • | 2.0 GB Fits | 2.8 GB Fits | 313 |
| 5-bit (Q5_K_M) • | 2.1 GB Fits | 2.9 GB Fits | 272 |
| 6-bit (Q6_K) • | 2.3 GB Fits | 3.1 GB Fits | 233 |
| 8-bit (Q8_0) • | 2.5 GB Fits | 3.3 GB Fits | 191 |
| 16-bit (F16/BF16) | 3.7 GB Fits | 4.5 GB Fits | 101 |
• real GGUF file size from TheBloke/deepseek-coder-1.3b-instruct-GGUF. Speed is a bandwidth ceiling (273 GB/s), not a benchmark. Methodology.
More
deepseek coder 1.3b instruct on every GPU and Mac · Every model that runs on the Mac M4 Pro 24GB · Apple Silicon guide · Try other settings in the calculator
Data: Hugging Face Hub (deepseek-ai/deepseek-coder-1.3b-instruct), Apple specs. Data as of 2026-11-17.