Only with CPU offload
Qwen3 235B-A22B at Q4_K_M needs 134.2 GB but only 14.4 GB is addressable, so about 91% of the layers would stream from system RAM at roughly 60 GB/s. Expect around 1.2 tokens per second — usable for batch work, painful for chat.
Workstation class. Realistically a 192 GB unified-memory or multi-GPU model.
Hardware requirements What hardware do I need to run Qwen3 235B-A22B? →At Q4_K_M with an 8K context: a 192 GB GPU (Instinct MI300X) or a 256 GB Mac (M3 Ultra). 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 | 232.5 GB | 234.6 GB | — | ~0.7 | −0.1% ppl | 220.2 GB over |
| Q6_K | 179.5 GB | 181.5 GB | — | ~0.9 | −0.4% ppl | 167.1 GB over |
| Q5_K_M | 155.1 GB | 157.2 GB | — | ~1.0 | −0.8% ppl | 142.8 GB over |
| Q4_K_M | 132.1 GB | 134.2 GB | — | ~1.2 | −1.9% ppl | 119.8 GB over |
| Q3_K_M | 107.0 GB | 109.0 GB | — | ~1.6 | −5.4% ppl | 94.6 GB over |
| Q2_K | 91.6 GB | 93.7 GB | — | ~1.9 | −15% ppl | 79.3 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
$ llama-server \
-hf Qwen/Qwen3-235B-A22B:Q4_K_M \
-c 8192 -ngl 8
The engine underneath most of the others. Every knob is exposed. More on llama.cpp.
Related models on a Radeon RX 9070 XT
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Qwen3 32B 32.8B · same family |
Q4_K_M · 21.0 GB | ~4.7 | CPU offload |
| Qwen3 30B-A3B 30.5B MoE · same family |
Q4_K_M · 18.5 GB | ~24 | CPU offload |
| Qwen3 Coder 30B-A3B 30.5B MoE · same family |
Q4_K_M · 18.5 GB | ~24 | CPU offload |
| Qwen3 14B 14.8B · same family |
Q4_K_M · 10.2 GB | 47 | Runs great |
| DeepSeek V4 Flash 284B-A13B 284B MoE · similar size |
Q4_K_M · 160.7 GB | ~2.1 | CPU offload |
| Qwen3.8-Flash-Next 180B-A6B 180B MoE · similar size |
Q4_K_M · 102.0 GB | ~4.7 | CPU offload |
| GLM-5.3-Flash 320B-A18B 321B MoE · similar size |
Q4_K_M · 181.2 GB | ~1.5 | CPU offload |
Qwen3 235B-A22B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
134.2 GB | ~1.2 | CPU offload |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
134.2 GB | ~1.2 | CPU offload |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
134.2 GB | — | Won't fit |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
134.2 GB | ~1.3 | CPU offload |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
134.2 GB | ~1.3 | CPU offload |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
134.2 GB | — | Won't fit |
| Instinct MI300X 190.4 GB usable · 5300 GB/s |
134.2 GB | 100 | Runs great |
| M3 Ultra · 256 GB 192.0 GB usable · 800 GB/s |
134.2 GB | 17 | Runs great |