Yi-VL 6B
01-ai/Yi-VL-6B
Parameters
6B
Context
4K
Downloads
249
Likes
124
Architecture
transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 17.7 GB RAM 32.0 · Disk 56.4 | 20.5 GB RAM 32.0 · Disk 82.4 | 37.0 GB RAM 55.5 · Disk 121.4 |
| FP88bit | 10.6 GB RAM 32.0 · Disk 47.7 | 13.1 GB RAM 32.0 · Disk 73.7 | 29.3 GB RAM 44.0 · Disk 112.7 |
| INT88bit | 10.6 GB RAM 32.0 · Disk 47.7 | 13.1 GB RAM 32.0 · Disk 73.7 | 29.3 GB RAM 44.0 · Disk 112.7 |
| AWQ4bit | 7.2 GB RAM 32.0 · Disk 43.5 | 9.6 GB RAM 32.0 · Disk 69.5 | 25.6 GB RAM 38.4 · Disk 108.5 |
| GPTQ4bit | 7.3 GB RAM 32.0 · Disk 43.6 | 9.6 GB RAM 32.0 · Disk 69.6 | 25.7 GB RAM 38.5 · Disk 108.6 |
| GGUF4bit | 7.4 GB RAM 32.0 · Disk 43.7 | 9.7 GB RAM 32.0 · Disk 69.7 | 25.7 GB RAM 38.6 · Disk 108.7 |
GPU Recommendations
1× RTX 3080 Ti
12 GB VRAM
≈ 314.5 tok/s
Effective production throughput ≈ 220.1 tok/s
score 0.6822
1× Tesla V100
16 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.6488
8× RTX 5090
256 GB VRAM
≈ 1977.4 tok/s
Effective production throughput ≈ 1384.2 tok/s
score 0.3506
1× RTX 3080
10 GB VRAM
≈ 262.1 tok/s
Effective production throughput ≈ 183.5 tok/s
score 0.6408
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
Tesla V100
16 GB VRAM
$40.6
/mo · vast
RTX 3080
10 GB VRAM
$64.3
/mo · vast
RTX 4070S Ti
16 GB VRAM
$68.9
/mo · vast
RTX 3080 Ti
12 GB VRAM
$69.2
/mo · vast
L4
24 GB VRAM
$76.2
/mo · vast