OctoCoder 15B
BigCode · dense · 15.5B parameters · 8,192 context
Parameters
15.5B
Context Window
8K tokens
Architecture
Dense
Best GPU
H100 SXM
Intelligence Brief
OctoCoder 15B is a 15.5B parameter DENSE model from BigCode, featuring Multi-Head Attention (MHA) with 40 layers and 6,144 hidden dimensions. With a 8,192 token context window, it supports code. For self-hosted inference, H100 SXM delivers optimal throughput at $1794/month.
Architecture Details
Memory Requirements
BF16 Weights
31.0 GB
FP8 Weights
15.5 GB
INT4 Weights
7.8 GB
GPU Compatibility Matrix
OctoCoder 15B is compatible with 82% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
FP8 · 1 GPU · tensorrt-llm
100/100
score
Throughput
1.1K tok/s
Latency (ITL)
1.0ms
Est. TTFT
0ms
Cost/Month
$1794
Cost/M Tokens
$0.65
FP8 · 1 GPU · tensorrt-llm
95/100
score
Throughput
1.1K tok/s
Latency (ITL)
1.0ms
Est. TTFT
0ms
Cost/Month
$1794
Cost/M Tokens
$0.65
BF16 · 1 GPU · vllm
95/100
score
Throughput
133.8 tok/s
Latency (ITL)
7.5ms
Est. TTFT
1ms
Cost/Month
$465
Cost/M Tokens
$1.32
Deployment Options
API Deployment
No API pricing available
Single GPU
H100 SXM
$1794/mo
Min VRAM: 16 GB
Multi-GPU
RTX 3090 x2
272.1 tok/s
TP· $361/mo
API Pricing Comparison
No API pricing data available for this model.
Performance Estimates
Throughput by GPU
VRAM Breakdown (H100 SXM, FP8)
Precision Impact
bf16
31.0 GB
weights/GPU
fp8
15.5 GB
weights/GPU
~1.1K tok/s
int4
7.8 GB
weights/GPU
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy OctoCoder 15B
Self-Hosted Infrastructure
Similar Models
StarCoder2 15B
15.5B params · dense
Quality: 42
from $0.30/M
DeepSeek V2 Lite
15.7B params · moe
Quality: 50
Nemotron 15B
15B params · dense
Quality: 72
from $0.30/M
CodeGen2 16B
16B params · dense
Quality: 50
Qwen 2.5 14B
14.8B params · dense
Quality: 76
from $0.30/M
Frequently Asked Questions
How much VRAM does OctoCoder 15B need for inference?
OctoCoder 15B requires approximately 31.0 GB of VRAM at BF16 precision, 15.5 GB at FP8, or 7.8 GB at INT4 quantization. Additional VRAM is needed for KV-cache (983040 bytes per token) and activations (~1.20 GB).
What is the best GPU for OctoCoder 15B?
The top recommended GPU for OctoCoder 15B is the H100 SXM using FP8 precision. It achieves approximately 1.1K tokens/sec at an estimated cost of $1794/month ($0.65/M tokens). Score: 100/100.
How much does OctoCoder 15B inference cost?
OctoCoder 15B inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.