Yes — with 15.0 GB to spare
Qwen2.5-Coder 32B at Q4_K_M fits your M4 Max · 48 GB entirely in unified memory at 8K context, at an estimated 17 tokens per second. Past 67K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.
The first local code model that felt competitive with hosted assistants. Qwen3.8 27B is smaller and far ahead on agentic work.
Hardware requirements What hardware do I need to run Qwen2.5-Coder 32B? →At Q4_K_M with an 8K context: a 32 GB GPU (RTX 5090) or a 36 GB Mac (M4 Max). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 32.5 GB | 35.1 GB | 11K | 9.4 | −0.1% ppl | Fits |
| Q6_K | 25.0 GB | 27.6 GB | 41K | 12 | −0.4% ppl | Long context |
| Q5_K_M | 21.7 GB | 24.3 GB | 54K | 14 | −0.8% ppl | Long context |
| Q4_K_M | 18.4 GB | 21.0 GB | 67K | 17 | −1.9% ppl | Recommended |
| Q3_K_M | 14.9 GB | 17.5 GB | 81K | 20 | −5.4% ppl | Long context |
| Q2_K | 12.8 GB | 15.4 GB | 90K | 24 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.
How to run it
$ pip install mlx-lm $ mlx_lm.generate --model mlx-community/Qwen2.5-Coder-32B-Instruct-4bit \ --max-tokens 512 --prompt "Hello"
Apple's own array framework. The fastest path on Apple Silicon. More on MLX.
Related models on an M4 Max · 48 GB
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Qwen2.5-Coder 14B 14.8B · same family |
Q4_K_M · 10.4 GB | 37 | Runs great |
| Qwen2.5-Coder 7B 7.62B · same family |
Q4_K_M · 5.3 GB | 71 | Runs great |
| Qwen3 32B 32.8B · similar size |
Q4_K_M · 21.0 GB | 17 | Runs great |
| DeepSeek-R1-Distill-Qwen 32B 32.8B · similar size |
Q4_K_M · 21.0 GB | 17 | Runs great |
| LLM-jp 4 33B Thinking 33.2B · similar size |
Q4_K_M · 21.3 GB | 16 | Runs great |
| Olmo 3.1 32B Instruct 32.2B · similar size |
Q4_K_M · 20.0 GB | 17 | Runs great |
| Nemotron 3.5 Lightning 30B-A3B 31.6B MoE · similar size |
Q4_K_M · 18.4 GB | 79 | Runs great |
Qwen2.5-Coder 32B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
21.0 GB | — | Won't fit |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
21.0 GB | ~3.1 | CPU offload |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
21.0 GB | — | Won't fit |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
21.0 GB | 33 | Tight fit |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
21.0 GB | 32 | Tight fit |
| GeForce RTX 5090 30.4 GB usable · 1792 GB/s |
21.0 GB | 59 | Runs great |
| M4 Max · 36 GB 27.0 GB usable · 410 GB/s |
21.0 GB | 12 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
21.0 GB | 12 | Runs great |