timm/efficientnet_b3.ra2_in1k
timm/efficientnet_b3.ra2_in1k
Parameters
12.3M
Context
—
Downloads
12.7M
Likes
30
Architecture
—
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 3.6 GB RAM 32.0 · Disk 39.0 | 5.8 GB RAM 32.0 · Disk 65.0 | 21.6 GB RAM 32.5 · Disk 104.0 |
| FP88bit | 3.6 GB RAM 32.0 · Disk 39.0 | 5.8 GB RAM 32.0 · Disk 65.0 | 21.6 GB RAM 32.4 · Disk 104.0 |
| INT88bit | 3.6 GB RAM 32.0 · Disk 39.0 | 5.8 GB RAM 32.0 · Disk 65.0 | 21.6 GB RAM 32.4 · Disk 104.0 |
| AWQ4bit | 3.6 GB RAM 32.0 · Disk 39.0 | 5.8 GB RAM 32.0 · Disk 65.0 | 21.6 GB RAM 32.4 · Disk 104.0 |
| GPTQ4bit | 3.6 GB RAM 32.0 · Disk 39.0 | 5.8 GB RAM 32.0 · Disk 65.0 | 21.6 GB RAM 32.4 · Disk 104.0 |
| GGUF4bit | 3.6 GB RAM 32.0 · Disk 39.0 | 5.8 GB RAM 32.0 · Disk 65.0 | 21.6 GB RAM 32.4 · Disk 104.0 |
GPU Recommendations
1× RTX 3080 Ti
12 GB VRAM
≈ 91200 tok/s
Effective production throughput ≈ 63840 tok/s
score 0.6229
1× Tesla V100
16 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.5852
8× RTX 5090
256 GB VRAM
≈ 573440 tok/s
Effective production throughput ≈ 401408 tok/s
score 0.3488
1× RTX 4060 Ti
8 GB VRAM
≈ 28800 tok/s
Effective production throughput ≈ 20160 tok/s
score 0.6828
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
Tesla V100
16 GB VRAM
$39.7
/mo · vast
RTX 4060 Ti
8 GB VRAM
$59.5
/mo · vast
RTX 5060 Ti
8 GB VRAM
$67.5
/mo · vast
RTX 4070S Ti
16 GB VRAM
$68.5
/mo · vast
RTX 3080
10 GB VRAM
$72.6
/mo · vast