Home / Models / Qwen3 235B-A22B
Qwen3 235B-A22B
235B parameters · 22B active · native context 40,960 · qwen3_moe
Estimated VRAM requirement
Weight memory uses parameter count × bits per weight, plus a quantization overhead factor. KV cache uses standard GQA formulas. Values are calculated estimates, not measured allocations.
| Quantization | Estimated weights | 2K total | 4K total | 8K total | 16K total | 32K total | 40K total |
|---|---|---|---|---|---|---|---|
| FP16 | 446.7 GB | 483.5 GB | 483.9 GB | 484.6 GB | 486.1 GB | 489.0 GB | 490.5 GB |
| Q8 | 251.2 GB | 272.5 GB | 272.8 GB | 273.6 GB | 275.0 GB | 278.0 GB | 279.4 GB |
| Q6 | 195.7 GB | 212.5 GB | 212.8 GB | 213.6 GB | 215.0 GB | 218.0 GB | 219.4 GB |
| Q5 | 165.6 GB | 179.9 GB | 180.3 GB | 181.0 GB | 182.5 GB | 185.5 GB | 186.9 GB |
| Q4 | 137.9 GB | 150.1 GB | 150.5 GB | 151.2 GB | 152.7 GB | 155.6 GB | 157.1 GB |
| Q3 | 110.2 GB | 120.1 GB | 120.5 GB | 121.2 GB | 122.7 GB | 125.6 GB | 127.1 GB |
Find a GPU for this model
Run at the quantization and context selected below. Defaults are Q4 and 8K when you do not change the controls. Results are full-VRAM fits only — not a speed ranking.
- Run at
- Q4 · 8K context
- Required VRAM
- 151.2 GB
No fresh matched Amazon price is currently available for a full-VRAM fit. See compatible GPUs · Workstations · Rent a server · Buy vs rent.
Lowest-cost full-VRAM option
Sorted by lowest current Amazon price among GPUs that fit entirely in VRAM. This is not a performance ranking.
No compatible GPU currently has a fresh Amazon price.
More VRAM headroom
Sorted by leftover usable VRAM after the calculated requirement. Headroom is not tokens/sec.
NVIDIA B200 192 GB
- GPU VRAM
- 192 GB advertised
- Required VRAM
- 151.2 GB
- Usable GPU VRAM
- 172.8 GB
- VRAM headroom
- 21.6 GB — leftover usable memory after the calculated requirement, not a speed ranking
- Compatible
- Yes — fits entirely in VRAM
- Product SKUs
- 0 mapped · 0 Amazon-matched
- Amazon
- Check availability
Compatible GPUs
Status is a calculated memory fit against usable VRAM (advertised × 0.9). Open a GPU to see product SKUs and Amazon listings.
Sources
Model specifications: official repository Qwen/Qwen3-235B-A22B · revision main. Compatibility: RigForAI calculator v1.0.0 (estimated VRAM). GPU products: Icecat. Amazon is a separate affiliate match and is not used as a spec source.