Skip to content
Updated minutes ago
Meta

Code Llama 13B

Meta · dense · 13B parameters · 16,384 context

Quality
44.0

Architecture Details

TypeDENSE
Total Parameters13B
Active Parameters13B
Layers40
Hidden Dimension5,120
Attention Heads40
KV Heads40
Head Dimension128
Vocab Size32,016

Memory Requirements

BF16 Weights

26.0 GB

FP8 Weights

13.0 GB

INT4 Weights

6.5 GB

KV-Cache per Token819200 bytes
Activation Estimate1.50 GB

Fits on (single-node)

B200 SXM BF16B100 SXM BF16GB200 NVL72 (per GPU) BF16GB300 NVL72 (per GPU) BF16H200 SXM BF16H100 SXM BF16H100 PCIe BF16H100 NVL BF16

GPU Recommendations

A100 40GB SXMoptimal

BF16 · 1 GPU · vllm

95/100

score

Throughput

322.9 tok/s

Cost/Month

$807

Cost/M Tokens

$0.95

Use this config →
RTX A6000optimal

BF16 · 1 GPU · vllm

95/100

score

Throughput

159.5 tok/s

Cost/Month

$465

Cost/M Tokens

$1.11

Use this config →
A40optimal

BF16 · 1 GPU · vllm

95/100

score

Throughput

144.5 tok/s

Cost/Month

$399

Cost/M Tokens

$1.05

Use this config →

API Pricing Comparison

ProviderInput $/MOutput $/MBadges
together$0.22$0.22
Cheapest

Quality Benchmarks

MMLU
47.0
HumanEval
36.0
GSM8K
35.0
MT-Bench
63.0

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

vllmsglangtgitensorrt-llmollama

Supported Precisions

BF16 (default)FP8INT4

Similar Models