Can an M4 Pro 24GB Mac run DeepSeek-R1-Distill-Qwen-32B?
M4 Pro · 24 GB unified memory · 273 GB/s · Mac mini (M4 Pro), MacBook Pro 14" (M4 Pro)
DeepSeek-R1-Distill-Qwen-32B needs about 22.4 GiB but an M4 Pro 24GB Mac has only ~20.4 GiB available for a model — you are 2.0 GiB short. macOS will swap to SSD and generation will crawl. There is a smaller quantisation that fits: see below.
Where the memory goes
Three things occupy memory when a model is loaded: the weights themselves, the KV cache that holds the conversation, and the runtime's own working buffers. Only the first is fixed — the KV cache grows with every token in your context.
| Quantisation | Weights | Total | Tok/s | Fits? |
|---|---|---|---|---|
| FP16 | 61.1 GiB | 66.9 GiB | 3 | No |
| Q8_0 | 32.5 GiB | 36.9 GiB | 6 | No |
| Q6_K | 25.2 GiB | 29.3 GiB | 8 | No |
| Q5_K_M | 21.8 GiB | 25.7 GiB | 9 | No |
| Q4_K_M | 18.7 GiB | 22.4 GiB | 11 | No |
| Q3_K_M | 14.9 GiB | 18.4 GiB | 14 | Yes, but tight |
| Q2_K | 11.5 GiB | 14.8 GiB | 18 | Yes, comfortably |
The default. Best quality-per-gigabyte for most people.
How long a context fits
The KV cache is often what breaks a setup that looked fine at load time. Quantising it to 8-bit roughly halves its footprint with little measurable quality cost.
| Context | KV cache | Total | FP16 KV | Q8 KV |
|---|---|---|---|---|
| 2K | 0.5 GiB | 20.7 GiB | No | No |
| 4K | 1.0 GiB | 21.3 GiB | No | No |
| 8K | 2.0 GiB | 22.4 GiB | No | No |
| 16K | 4.0 GiB | 24.7 GiB | No | No |
| 32K | 8.0 GiB | 29.3 GiB | No | No |
| 128K | 32.0 GiB | 56.9 GiB | No | No |
What to run instead on an M4 Pro 24GB Mac
These are the largest models that fit comfortably on this machine at Q4_K_M with an 8K context.
| Model | Size | Total | Tok/s | |
|---|---|---|---|---|
| Mistral Small 3 24B | 23.6B | 16.2 GiB | 15 | Yes, comfortably |
| gpt-oss-20b | 20.9B | 13.7 GiB | 62 | Yes, comfortably |
| DeepSeek-R1-Distill-Qwen-14B | 14.8B | 11.2 GiB | 24 | Yes, comfortably |
| Qwen2.5 14B | 14.8B | 11.2 GiB | 24 | Yes, comfortably |
| Qwen2.5-Coder 14B | 14.8B | 11.2 GiB | 24 | Yes, comfortably |
| Qwen3 14B | 14.8B | 10.9 GiB | 24 | Yes, comfortably |
Macs that run DeepSeek-R1-Distill-Qwen-32B comfortably
The smallest configuration that handles it is the M1 Max 32GB (MacBook Pro 14" (M1 Max)).
| Mac | Memory | Bandwidth | Tok/s |
|---|---|---|---|
| M1 Max 32GB | 32 GB | 400 GB/s | 16 |
| M2 Max 32GB | 32 GB | 400 GB/s | 16 |
| M4 32GB | 32 GB | 120 GB/s | 5 |
| M3 Max 36GB | 36 GB | 300 GB/s | 12 |
| M4 Max 36GB | 36 GB | 410 GB/s | 16 |
| M4 Pro 48GB | 48 GB | 273 GB/s | 11 |
| M4 Max 48GB | 48 GB | 546 GB/s | 22 |
| M1 Max 64GB | 64 GB | 400 GB/s | 16 |
| M2 Ultra 64GB | 64 GB | 800 GB/s | 32 |
| M4 Pro 64GB | 64 GB | 273 GB/s | 11 |
| M4 Max 64GB | 64 GB | 546 GB/s | 22 |
| M2 Max 96GB | 96 GB | 400 GB/s | 16 |
Common questions
- Can an M4 Pro 24GB Mac run DeepSeek-R1-Distill-Qwen-32B?
- No. At Q4_K_M it needs about 22.4 GiB, and an M4 Pro 24GB Mac has roughly 20.4 GiB available for a model after macOS takes its share.
- How fast is DeepSeek-R1-Distill-Qwen-32B on an Mac?
- Around 11 tokens per second. Token generation on Apple Silicon is limited by memory bandwidth, and this machine has 273 GB/s.
- How much memory does DeepSeek-R1-Distill-Qwen-32B need?
- 18.7 GiB for the weights at Q4_K_M, plus 2.0 GiB for an 8K-token KV cache and about 1.7 GiB of runtime overhead — 22.4 GiB in total.