Written by Jakub Rusinowski · Last updated April 28, 2025
Yes — comfortably
Yes, comfortably — Qwen 3 235B-A22B (MoE) at Q3_K_M needs about 102.5 GB of the 204.8 GB usable on 256 GB system RAM, leaving ~102.3 GB spare and running at ~6.5 tok/s (estimated), with room for about 65,536 tokens of context.
Confidence: high · Recommended quantization: Q3_K_M · Estimated speed: ~6.5 tok/s
| Usable memory for models | 204.8 GB |
| Memory bandwidth | 90 GB/s |
| Quant | Memory needed | Fits 204.8 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 472.4 GB | ✗ No | — | — | 470 GB |
| Q8_0 | 252.1 GB | ✗ No | — | — | 249.7 GB |
| Q6_K | 195.1 GB | ✓ Yes | 32K | ~3.5 tok/s | 192.7 GB |
| Q5_K_M | 168.9 GB | ✓ Yes | 64K | ~4.1 tok/s | 166.6 GB |
| Q4_K_M | 144.3 GB | ✓ Yes | 64K | ~4.7 tok/s | 141.9 GB |
| Q3_K_M | 102.5 GB | ✓ Yes | 64K | ~6.5 tok/s | 100.2 GB |
| Q2_K | 79.6 GB | ✓ Yes | 64K | ~8.2 tok/s | 77.3 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Qwen 3 235B-A22B (MoE) | 144.3 GB | ✓ Fits | ~4.7 tok/s |
| Qwen 3 32B | 22.8 GB | ✓ Fits | ~3.2 tok/s |
| Qwen 3 30B-A3B (MoE) | 20 GB | ✓ Fits | ~26.4 tok/s |
| Qwen 3 14B | 11.1 GB | ✓ Fits | ~6.9 tok/s |
| Qwen 3 8B | 7 GB | ✓ Fits | ~11.8 tok/s |
llama.cpp (CPU build) or Ollama — both run without a GPU
Yes, comfortably — Qwen 3 235B-A22B (MoE) at Q3_K_M needs about 102.5 GB of the 204.8 GB usable on 256 GB system RAM, leaving ~102.3 GB spare and running at ~6.5 tok/s (estimated), with room for about 65,536 tokens of context.
Q3_K_M — it needs about 102.5 GB of the 204.8 GB available, downloads as roughly 100.2 GB, and runs at an estimated 6.5 tokens/sec with up to 64K of context.
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
llama.cpp (CPU build) or Ollama — both run without a GPU