Yi-VL 34B
01-ai/Yi-VL-34B
Parameters
34B
Context
4K
Downloads
221
Likes
265
Architecture
transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 83.7 GB RAM 125.5 · Disk 137.8 | 89.5 GB RAM 134.3 · Disk 163.8 | 109.0 GB RAM 163.5 · Disk 202.8 |
| FP88bit | 43.6 GB RAM 65.5 · Disk 88.4 | 47.6 GB RAM 71.4 · Disk 114.4 | 65.3 GB RAM 98.0 · Disk 153.4 |
| INT88bit | 43.6 GB RAM 65.5 · Disk 88.4 | 47.6 GB RAM 71.4 · Disk 114.4 | 65.3 GB RAM 98.0 · Disk 153.4 |
| AWQ4bit | 24.4 GB RAM 36.5 · Disk 64.6 | 27.5 GB RAM 41.2 · Disk 90.6 | 44.3 GB RAM 66.4 · Disk 129.6 |
| GPTQ4bit | 24.6 GB RAM 36.9 · Disk 64.9 | 27.7 GB RAM 41.6 · Disk 90.9 | 44.5 GB RAM 66.8 · Disk 129.9 |
| GGUF4bit | 25.1 GB RAM 37.7 · Disk 65.6 | 28.3 GB RAM 42.4 · Disk 91.6 | 45.1 GB RAM 67.6 · Disk 130.6 |
GPU Recommendations
1× H100 SXM
80 GB VRAM
≈ 203.9 tok/s
Effective production throughput ≈ 142.7 tok/s
score 0.5811
2× Tesla V100
32 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.6177
8× H200 SXM
1128 GB VRAM
≈ 934.9 tok/s
Effective production throughput ≈ 654.4 tok/s
score 0.2197
1× RTX A6000
48 GB VRAM
≈ 46.7 tok/s
Effective production throughput ≈ 32.7 tok/s
score 0.6437
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
RTX A6000
48 GB VRAM
$210
/mo · vast
RTX 5090
32 GB VRAM
$236
/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