Code Llama 13B
Meta · dense · 13B parameters · 16,384 context
Parameters
13B
Context Window
16K tokens
Architecture
Dense
Best GPU
A100 40GB SXM
Cheapest API
$0.22/M
Quality Score
44/100
Intelligence Brief
Code Llama 13B is a 13B parameter DENSE model from Meta, featuring Multi-Head Attention (MHA) with 40 layers and 5,120 hidden dimensions. With a 16,384 token context window, it supports code, math. On standardized benchmarks, it achieves MMLU 47, HumanEval 36, GSM8K 35. The most cost-effective API deployment is via together at $0.22/M output tokens. For self-hosted inference, A100 40GB SXM delivers optimal throughput at $807/month.
Architecture Details
Memory Requirements
BF16 Weights
26.0 GB
FP8 Weights
13.0 GB
INT4 Weights
6.5 GB
GPU Compatibility Matrix
Code Llama 13B is compatible with 82% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
BF16 · 1 GPU · vllm
95/100
score
Throughput
322.9 tok/s
Latency (ITL)
3.1ms
Est. TTFT
1ms
Cost/Month
$807
Cost/M Tokens
$0.95
BF16 · 1 GPU · vllm
95/100
score
Throughput
159.5 tok/s
Latency (ITL)
6.3ms
Est. TTFT
1ms
Cost/Month
$465
Cost/M Tokens
$1.11
BF16 · 1 GPU · vllm
95/100
score
Throughput
144.5 tok/s
Latency (ITL)
6.9ms
Est. TTFT
1ms
Cost/Month
$399
Cost/M Tokens
$1.05
Deployment Options
API Deployment
together
$0.22/M
output tokens
Single GPU
A100 40GB SXM
$807/mo
Min VRAM: 13 GB
Multi-GPU
RTX 3090 x2
319.5 tok/s
TP· $361/mo
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| together | $0.22 | $0.22 | Cheapest |
Cost Analysis
| Provider | Input $/M | Output $/M | ~Monthly Cost |
|---|---|---|---|
| togetherBest Value | $0.22 | $0.22 | $2 |
Cost per 1,000 Requests
Short (500 tok)
$0.15
via together
Medium (2K tok)
$0.62
via together
Long (8K tok)
$2.20
via together
Performance Estimates
Throughput by GPU
VRAM Breakdown (A100 40GB SXM, BF16)
Precision Impact
bf16
26.0 GB
weights/GPU
~322.9 tok/s
fp8
13.0 GB
weights/GPU
int4
6.5 GB
weights/GPU
Quality Benchmarks
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy Code Llama 13B
Similar Models
Code Llama 7B
7B params · dense
Quality: 39
from $0.20/M
Code Llama 34B
34B params · dense
Quality: 55
from $0.78/M
OLMo 2 13B
13B params · dense
Quality: 50
Baichuan 2 13B
13B params · dense
Quality: 50
from $0.25/M
Vicuna 13B
13B params · dense
Quality: 50
Frequently Asked Questions
How much VRAM does Code Llama 13B need for inference?
Code Llama 13B requires approximately 26.0 GB of VRAM at BF16 precision, 13.0 GB at FP8, or 6.5 GB at INT4 quantization. Additional VRAM is needed for KV-cache (819200 bytes per token) and activations (~1.50 GB).
What is the best GPU for Code Llama 13B?
The top recommended GPU for Code Llama 13B is the A100 40GB SXM using BF16 precision. It achieves approximately 322.9 tokens/sec at an estimated cost of $807/month ($0.95/M tokens). Score: 95/100.
How much does Code Llama 13B inference cost?
Code Llama 13B API inference starts from $0.22/M input tokens and $0.22/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.