InternVL2 8B
OpenGVLab/InternVL2-8B
Parameters
8.1B
Context
8K
Downloads
114.3K
Likes
186
Architecture
transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 22.7 GB RAM 34.0 · Disk 62.5 | 25.7 GB RAM 38.6 · Disk 88.5 | 42.4 GB RAM 63.6 · Disk 127.5 |
| FP88bit | 13.1 GB RAM 32.0 · Disk 50.8 | 15.7 GB RAM 32.0 · Disk 76.8 | 32.0 GB RAM 48.0 · Disk 115.8 |
| INT88bit | 13.1 GB RAM 32.0 · Disk 50.8 | 15.7 GB RAM 32.0 · Disk 76.8 | 32.0 GB RAM 48.0 · Disk 115.8 |
| AWQ4bit | 8.5 GB RAM 32.0 · Disk 45.1 | 10.9 GB RAM 32.0 · Disk 71.1 | 27.0 GB RAM 40.5 · Disk 110.1 |
| GPTQ4bit | 8.6 GB RAM 32.0 · Disk 45.2 | 11.0 GB RAM 32.0 · Disk 71.2 | 27.1 GB RAM 40.6 · Disk 110.2 |
| GGUF4bit | 8.7 GB RAM 32.0 · Disk 45.3 | 11.1 GB RAM 32.0 · Disk 71.3 | 27.2 GB RAM 40.8 · Disk 110.3 |
GPU Recommendations
1× RTX 5080
16 GB VRAM
≈ 245.5 tok/s
Effective production throughput ≈ 171.9 tok/s
score 0.6771
1× Tesla V100
16 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.6717
8× H100 SXM
640 GB VRAM
≈ 2741.7 tok/s
Effective production throughput ≈ 1919.2 tok/s
score 0.2416
1× RTX 5070
12 GB VRAM
≈ 171.9 tok/s
Effective production throughput ≈ 120.3 tok/s
score 0.6507
💬 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
12 GB VRAM
$58.7
/mo · vast
RTX 5070 Ti
16 GB VRAM
$62.0
/mo · vast