Qwen3-VL-235B-A22B
Qwen/Qwen3-VL-235B-A22B-Instruct
Parameters
235B
Context
256K
Downloads
1.6M
Likes
412
Architecture
moe_transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 557.3 GB RAM 835.9 · Disk 721.9 | 584.6 GB RAM 877.0 · Disk 747.9 | 625.7 GB RAM 938.5 · Disk 786.9 |
| FP88bit | 280.4 GB RAM 420.7 · Disk 380.4 | 295.2 GB RAM 442.8 · Disk 406.4 | 323.6 GB RAM 485.4 · Disk 445.4 |
| INT88bit | 280.4 GB RAM 420.7 · Disk 380.4 | 295.2 GB RAM 442.8 · Disk 406.4 | 323.6 GB RAM 485.4 · Disk 445.4 |
| AWQ4bit | 147.2 GB RAM 220.8 · Disk 216.1 | 155.9 GB RAM 233.9 · Disk 242.1 | 178.3 GB RAM 267.4 · Disk 281.1 |
| GPTQ4bit | 148.9 GB RAM 223.4 · Disk 218.3 | 157.7 GB RAM 236.6 · Disk 244.3 | 180.2 GB RAM 270.3 · Disk 283.3 |
| GGUF4bit | 152.4 GB RAM 228.6 · Disk 222.5 | 161.3 GB RAM 242.0 · Disk 248.5 | 183.9 GB RAM 275.9 · Disk 287.5 |
GPU Recommendations
Best ValueBEST
1× B200
180 GB VRAM
$3,013/mo
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.5963
Cheapest
8× RTX 3090
192 GB VRAM
$636/mo
≈ 26.4 tok/s
Effective production throughput ≈ 18.5 tok/s
score 0.5516
Performance
8× H200 SXM
1128 GB VRAM
$20,440/mo
≈ 135.3 tok/s
Effective production throughput ≈ 94.7 tok/s
score 0.2197
Min Complexity
2× A100 80GB
160 GB VRAM
$1,752/mo
≈ 28.7 tok/s
Effective production throughput ≈ 20.1 tok/s
score 0.581
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
B200
180 GB VRAM
$3,013
/mo · vast
B200 SXM
180 GB VRAM
—