Llama 3.2 Vision 11B
meta-llama/Llama-3.2-11B-Vision-Instruct
Parameters
11B
Context
128K
Downloads
94.3K
Likes
1.6K
Architecture
transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 29.5 GB RAM 44.2 · Disk 71.0 | 32.9 GB RAM 49.3 · Disk 97.0 | 49.9 GB RAM 74.8 · Disk 136.0 |
| FP88bit | 16.5 GB RAM 32.0 · Disk 55.0 | 19.3 GB RAM 32.0 · Disk 81.0 | 35.7 GB RAM 53.6 · Disk 120.0 |
| INT88bit | 16.5 GB RAM 32.0 · Disk 55.0 | 19.3 GB RAM 32.0 · Disk 81.0 | 35.7 GB RAM 53.6 · Disk 120.0 |
| AWQ4bit | 10.3 GB RAM 32.0 · Disk 47.3 | 12.8 GB RAM 32.0 · Disk 73.3 | 28.9 GB RAM 43.4 · Disk 112.3 |
| GPTQ4bit | 10.4 GB RAM 32.0 · Disk 47.4 | 12.9 GB RAM 32.0 · Disk 73.4 | 29.0 GB RAM 43.5 · Disk 112.4 |
| GGUF4bit | 10.5 GB RAM 32.0 · Disk 47.6 | 13.0 GB RAM 32.0 · Disk 73.6 | 29.2 GB RAM 43.8 · Disk 112.6 |
GPU Recommendations
1× RTX 5090
32 GB VRAM
≈ 337.5 tok/s
Effective production throughput ≈ 236.2 tok/s
score 0.6044
1× Tesla V100
16 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.6766
8× H100 SXM
640 GB VRAM
≈ 2018.8 tok/s
Effective production throughput ≈ 1413.2 tok/s
score 0.2416
1× RTX 5070 Ti
16 GB VRAM
≈ 168.7 tok/s
Effective production throughput ≈ 118.1 tok/s
score 0.6821
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
Tesla V100
16 GB VRAM
$20.3
/mo · vast
RTX 4070S Ti
16 GB VRAM
$49.5
/mo · vast
RTX 4080S
16 GB VRAM
$50.0
/mo · vast
RTX 5070 Ti
16 GB VRAM
$62.0
/mo · vast
RTX 3090
24 GB VRAM
$79.5
/mo · vast