Yes — with 27.9 GB to spare
Qwen3 Coder 30B-A3B at Q4_K_M fits your RTX A6000 entirely on the GPU at 8K context, at an estimated 96 tokens per second. There is room for its full 256K window.
Agentic coding MoE with a 256K native window. Still the most-downloaded local code model.
Hardware requirements What hardware do I need to run Qwen3 Coder 30B-A3B? →At Q4_K_M with an 8K context: a 24 GB GPU (RTX 4090) or a 32 GB Mac (M4). 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 | 30.2 GB | 31.5 GB | 166K | 55 | −0.1% ppl | Long context |
| Q6_K | 23.3 GB | 24.6 GB | 240K | 71 | −0.4% ppl | Long context |
| Q5_K_M | 20.1 GB | 21.5 GB | 256K | 82 | −0.8% ppl | Long context |
| Q4_K_M | 17.1 GB | 18.5 GB | 256K | 96 | −1.9% ppl | Recommended |
| Q3_K_M | 13.9 GB | 15.2 GB | 256K | 119 | −5.4% ppl | Long context |
| Q2_K | 11.9 GB | 13.2 GB | 256K | 139 | −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
$ ollama pull qwen3-coder:30b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run qwen3-coder:30b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
Related models on an RTX A6000
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Qwen3 30B-A3B 30.5B MoE · same family |
Q4_K_M · 18.5 GB | 96 | Runs great |
| Qwen3 32B 32.8B · same family |
Q4_K_M · 21.0 GB | 25 | Runs great |
| Qwen3 14B 14.8B · same family |
Q4_K_M · 10.2 GB | 56 | Runs great |
| Qwen3 8B 8.19B · same family |
Q4_K_M · 6.3 GB | 101 | Runs great |
| GLM-4.7-Flash 30B-A3B 31.2B MoE · similar size |
Q4_K_M · 18.6 GB | 106 | Runs great |
| Muse Glimmer 30B 29.8B · similar size |
Q4_K_M · 17.5 GB | 28 | Runs great |
| Gemma 4 31B 31.3B · similar size |
Q4_K_M · 20.2 GB | 26 | Runs great |
Qwen3 Coder 30B-A3B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
18.5 GB | ~10 | CPU offload |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
18.5 GB | ~14 | CPU offload |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
18.5 GB | — | Won't fit |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
18.5 GB | 126 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
18.5 GB | 120 | Runs great |
| M4 · 32 GB 24.0 GB usable · 120 GB/s |
18.5 GB | 17 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
18.5 GB | 56 | Runs great |