No — not on this device
Qwen3 32B at Q4_K_M needs 21.0 GB against 10.7 GB usable, and the shortfall of 10.3 GB is more than 16 GB of system RAM can cover at a tolerable speed. A smaller sibling or a lower quantisation is the honest answer here.
The classic 24 GB target, and still the strongest local translator under 70B. Qwen3.8 27B is smaller and better at everything else.
Hardware requirements What hardware do I need to run Qwen3 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 | — | ~1.2 | −0.1% ppl | 24.4 GB over |
| Q6_K | 25.0 GB | 27.6 GB | — | ~1.5 | −0.4% ppl | 16.9 GB over |
| Q5_K_M | 21.7 GB | 24.3 GB | — | ~1.8 | −0.8% ppl | 13.6 GB over |
| Q4_K_M | 18.4 GB | 21.0 GB | — | ~2.1 | −1.9% ppl | 10.3 GB over |
| Q3_K_M | 14.9 GB | 17.5 GB | — | ~2.5 | −5.4% ppl | 6.8 GB over |
| Q2_K | 12.8 GB | 15.4 GB | — | ~3.0 | −15% ppl | 4.7 GB over |
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/Qwen3-32B-4bit \ --max-tokens 512 --prompt "Hello"
Apple's own array framework. The fastest path on Apple Silicon. More on MLX.
Related models on an M1 · 16 GB
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Qwen3 30B-A3B 30.5B MoE · same family |
Q4_K_M · 18.5 GB | — | Won't fit |
| Qwen3 Coder 30B-A3B 30.5B MoE · same family |
Q4_K_M · 18.5 GB | — | Won't fit |
| Qwen3 14B 14.8B · same family |
Q4_K_M · 10.2 GB | 4.6 | Tight fit |
| Qwen3 8B 8.19B · same family |
Q4_K_M · 6.3 GB | 8.3 | Runs great |
| DeepSeek-R1-Distill-Qwen 32B 32.8B · similar size |
Q4_K_M · 21.0 GB | — | Won't fit |
| Qwen2.5-Coder 32B 32.8B · similar size |
Q4_K_M · 21.0 GB | — | Won't fit |
| LLM-jp 4 33B Thinking 33.2B · similar size |
Q4_K_M · 21.3 GB | — | Won't fit |
Qwen3 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 |