Qwen3.5 35B-A3B
Qwen/Qwen3.5-35B-A3B
Parameters
35B
Context
256K
Downloads
2.1M
Likes
1.5K
Architecture
moe_transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 87.4 GB RAM 131.1 · Disk 140.7 | 106.9 GB RAM 160.4 · Disk 166.7 | 207.6 GB RAM 311.4 · Disk 205.7 |
| FP88bit | 46.2 GB RAM 69.3 · Disk 89.9 | 63.8 GB RAM 95.7 · Disk 115.9 | 162.6 GB RAM 243.9 · Disk 154.9 |
| INT88bit | 46.2 GB RAM 69.3 · Disk 89.9 | 63.8 GB RAM 95.7 · Disk 115.9 | 162.6 GB RAM 243.9 · Disk 154.9 |
| AWQ4bit | 26.3 GB RAM 39.5 · Disk 65.4 | 43.1 GB RAM 64.6 · Disk 91.4 | 140.9 GB RAM 211.4 · Disk 130.4 |
| GPTQ4bit | 26.6 GB RAM 39.9 · Disk 65.7 | 43.3 GB RAM 65.0 · Disk 91.7 | 141.2 GB RAM 211.8 · Disk 130.7 |
| GGUF4bit | 27.1 GB RAM 40.7 · Disk 66.3 | 43.9 GB RAM 65.8 · Disk 92.3 | 141.8 GB RAM 212.7 · Disk 131.3 |
GPU Recommendations
1× H100 SXM
80 GB VRAM
≈ 198.1 tok/s
Effective production throughput ≈ 138.7 tok/s
score 0.633
4× Tesla V100
64 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.5777
8× H200 SXM
1128 GB VRAM
≈ 908.3 tok/s
Effective production throughput ≈ 635.8 tok/s
score 0.2197
1× RTX A6000
48 GB VRAM
≈ 45.4 tok/s
Effective production throughput ≈ 31.8 tok/s
score 0.6519
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
RTX A6000
48 GB VRAM
$210
/mo · vast
L40S
48 GB VRAM
$341
/mo · vast
RTX PRO 6000 WS
48 GB VRAM
$482
/mo · vast
RTX PRO 6000 S
48 GB VRAM
$633
/mo · vast
A100 80GB
80 GB VRAM
$876
/mo · vast