Gemma 3n
google/gemma-3n
Parameters
1B
Context
8K
Downloads
0
Likes
0
Architecture
transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 5.9 GB RAM 32.0 · Disk 41.9 | 8.2 GB RAM 32.0 · Disk 67.9 | 24.2 GB RAM 36.3 · Disk 106.9 |
| FP88bit | 4.8 GB RAM 32.0 · Disk 40.5 | 7.0 GB RAM 32.0 · Disk 66.5 | 22.9 GB RAM 34.3 · Disk 105.5 |
| INT88bit | 4.8 GB RAM 32.0 · Disk 40.5 | 7.0 GB RAM 32.0 · Disk 66.5 | 22.9 GB RAM 34.3 · Disk 105.5 |
| AWQ4bit | 4.2 GB RAM 32.0 · Disk 39.8 | 6.4 GB RAM 32.0 · Disk 65.8 | 22.3 GB RAM 33.4 · Disk 104.8 |
| GPTQ4bit | 4.2 GB RAM 32.0 · Disk 39.8 | 6.4 GB RAM 32.0 · Disk 65.8 | 22.3 GB RAM 33.4 · Disk 104.8 |
| GGUF4bit | 4.2 GB RAM 32.0 · Disk 39.8 | 6.4 GB RAM 32.0 · Disk 65.8 | 22.3 GB RAM 33.4 · Disk 104.8 |
GPU Recommendations
1× RTX 5080
16 GB VRAM
≈ 2000 tok/s
Effective production throughput ≈ 1400 tok/s
score 0.6015
1× Tesla V100
16 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.5961
8× RTX 5090
256 GB VRAM
≈ 11946.7 tok/s
Effective production throughput ≈ 8362.7 tok/s
score 0.3617
1× RTX 5060 Ti
8 GB VRAM
≈ 933.3 tok/s
Effective production throughput ≈ 653.3 tok/s
score 0.6794
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
Tesla V100
16 GB VRAM
$20.3
/mo · vast
RTX 5060 Ti
8 GB VRAM
$39.7
/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