TranslateGemma 4B
google/translategemma-4b-it
Parameters
4.3B
Context
128K
Downloads
112.2K
Likes
819
Architecture
transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 15.1 GB RAM 32.0 · Disk 51.5 | 31.3 GB RAM 46.9 · Disk 77.5 | 128.7 GB RAM 193.0 · Disk 116.5 |
| FP88bit | 10.0 GB RAM 32.0 · Disk 45.3 | 26.0 GB RAM 39.0 · Disk 71.3 | 123.1 GB RAM 184.7 · Disk 110.3 |
| INT88bit | 10.0 GB RAM 32.0 · Disk 45.3 | 26.0 GB RAM 39.0 · Disk 71.3 | 123.1 GB RAM 184.7 · Disk 110.3 |
| AWQ4bit | 7.6 GB RAM 32.0 · Disk 42.2 | 23.5 GB RAM 35.2 · Disk 68.2 | 120.5 GB RAM 180.7 · Disk 107.2 |
| GPTQ4bit | 7.6 GB RAM 32.0 · Disk 42.3 | 23.5 GB RAM 35.2 · Disk 68.3 | 120.5 GB RAM 180.8 · Disk 107.3 |
| GGUF4bit | 7.7 GB RAM 32.0 · Disk 42.4 | 23.6 GB RAM 35.3 · Disk 68.4 | 120.6 GB RAM 180.9 · Disk 107.4 |
GPU Recommendations
1× RTX 5090
32 GB VRAM
≈ 861.5 tok/s
Effective production throughput ≈ 603.1 tok/s
score 0.6921
1× RTX 3090
24 GB VRAM
≈ 450 tok/s
Effective production throughput ≈ 315 tok/s
score 0.6415
8× H200 SXM
1128 GB VRAM
≈ 7384.6 tok/s
Effective production throughput ≈ 5169.2 tok/s
score 0.2197
1× RTX 4090
24 GB VRAM
≈ 484.6 tok/s
Effective production throughput ≈ 339.2 tok/s
score 0.6399
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
RTX 3090
24 GB VRAM
$88.4
/mo · vast
A10
24 GB VRAM
$171
/mo · vast
L4
24 GB VRAM
$185
/mo · vast
RTX 4090
24 GB VRAM
$190
/mo · tensordock
A100 SXM4
80 GB VRAM
$244
/mo · vast