Coding AIMIT
Replit Code 3B
replit/replit-code-v1_5-3b
Parameters
3.3B
Context
4K
Downloads
130
Likes
316
Architecture
transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 12.7 GB RAM 32.0 · Disk 48.6 | 28.8 GB RAM 43.2 · Disk 74.6 | 126.1 GB RAM 189.1 · Disk 113.6 |
| FP88bit | 8.8 GB RAM 32.0 · Disk 43.8 | 24.8 GB RAM 37.2 · Disk 69.8 | 121.8 GB RAM 182.8 · Disk 108.8 |
| INT88bit | 8.8 GB RAM 32.0 · Disk 43.8 | 24.8 GB RAM 37.2 · Disk 69.8 | 121.8 GB RAM 182.8 · Disk 108.8 |
| AWQ4bit | 7.0 GB RAM 32.0 · Disk 41.5 | 22.8 GB RAM 34.2 · Disk 67.5 | 119.8 GB RAM 179.7 · Disk 106.5 |
| GPTQ4bit | 7.0 GB RAM 32.0 · Disk 41.5 | 22.8 GB RAM 34.3 · Disk 67.5 | 119.8 GB RAM 179.7 · Disk 106.5 |
| GGUF4bit | 7.0 GB RAM 32.0 · Disk 41.6 | 22.9 GB RAM 34.3 · Disk 67.6 | 119.9 GB RAM 179.8 · Disk 106.6 |
GPU Recommendations
Best ValueBEST
1× RTX 5090
32 GB VRAM
$294/mo
≈ 1127 tok/s
Effective production throughput ≈ 788.9 tok/s
score 0.6868
Cheapest
1× RTX 3090
24 GB VRAM
$88.4/mo
≈ 588.7 tok/s
Effective production throughput ≈ 412.1 tok/s
score 0.6415
Performance
8× H200 SXM
1128 GB VRAM
$20,440/mo
≈ 9660.4 tok/s
Effective production throughput ≈ 6762.3 tok/s
score 0.2197
Min Complexity
1× RTX 4090
24 GB VRAM
$190/mo
≈ 634 tok/s
Effective production throughput ≈ 443.8 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
RTX A6000
48 GB VRAM
$292
/mo · vast