Replit Code v1.5 3B
Replit · dense · 3.3B parameters · 4,096 context
Parameters
3.3B
Context Window
4K tokens
Architecture
Dense
Best GPU
RTX 4070 Ti
Intelligence Brief
Replit Code v1.5 3B is a 3.3B parameter DENSE model from Replit, featuring Multi-Head Attention (MHA) with 32 layers and 2,560 hidden dimensions. With a 4,096 token context window, it supports code. For self-hosted inference, RTX 4070 Ti delivers optimal throughput at $237/month.
Recent changes
Loading…
Related models
3 suggestions
SantaCoder 1.1BSantaCoder · 1.1B—
Qwen 2.5 Coder 1.5BQwen 2.5 Coder · 1.5B—- Qwen 2.5 Coder 3BQwen 2.5 Coder · 3.1B—
Picks: same family first, then same vendor within ±2× params, then top tag-overlap matches. Price shown is the cheapest Output $/M across providers — the row's page shows the canonical anchor.
Architecture Details
Memory Requirements
BF16 Weights
6.6 GB
FP8 Weights
3.3 GB
INT4 Weights
1.6 GB
GPU Compatibility Matrix
Replit Code v1.5 3B is compatible with 100% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
BF16 · 1 GPU · vllm
100/100
score
Throughput
371.1 tok/s
Latency (ITL)
2.7ms
Est. TTFT
0ms
Cost/Month
$237
Cost/M Tokens
$0.24
BF16 · 1 GPU · vllm
100/100
score
Throughput
559.6 tok/s
Latency (ITL)
1.8ms
Est. TTFT
0ms
Cost/Month
$133
Cost/M Tokens
$0.09
BF16 · 1 GPU · vllm
100/100
score
Throughput
371.1 tok/s
Latency (ITL)
2.7ms
Est. TTFT
0ms
Cost/Month
$209
Cost/M Tokens
$0.21
Deployment Options
API Deployment
No API pricing available
Single GPU
RTX 4070 Ti
$237/mo
Min VRAM: 3 GB
Multi-GPU
RTX 4070 Ti
371.1 tok/s
Best available config
API Pricing Comparison
No API pricing data available for this model.
Performance Estimates
Throughput by GPU
VRAM Breakdown (RTX 4070 Ti, BF16)
Precision Impact
bf16
6.6 GB
weights/GPU
~371.1 tok/s
fp8
3.3 GB
weights/GPU
int4
1.6 GB
weights/GPU
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy Replit Code v1.5 3B
Self-Hosted Infrastructure
Similar Models
Llama 3.2 3B
3.21B params · dense
Quality: 55
from $0.06/M
Qwen 2.5 Coder 3B
3.1B params · dense
Quality: 50
DALL-E 3
3.5B params · dense
Quality: 50
from $40.00/M
Stable Diffusion XL 1.0
3.5B params · dense
Quality: 50
Qwen 2.5 3B
3.09B params · dense
Quality: 58
from $0.10/M
Frequently Asked Questions
How much VRAM does Replit Code v1.5 3B need for inference?
Replit Code v1.5 3B requires approximately 6.6 GB of VRAM at BF16 precision, 3.3 GB at FP8, or 1.6 GB at INT4 quantization. Additional VRAM is needed for KV-cache (163840 bytes per token) and activations (~0.40 GB).
What is the best GPU for Replit Code v1.5 3B?
The top recommended GPU for Replit Code v1.5 3B is the RTX 4070 Ti using BF16 precision. It achieves approximately 371.1 tokens/sec at an estimated cost of $237/month ($0.24/M tokens). Score: 100/100.
How much does Replit Code v1.5 3B inference cost?
Replit Code v1.5 3B inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.