Skip to content
Updated minutes ago
BigCode

StarCoder2 7B

BigCode · dense · 6.73B parameters · 16,384 context

Quality
35.0

Architecture Details

TypeDENSE
Total Parameters6.73B
Active Parameters6.73B
Layers32
Hidden Dimension4,608
Attention Heads36
KV Heads4
Head Dimension128
Vocab Size49,152

Memory Requirements

BF16 Weights

13.5 GB

FP8 Weights

6.7 GB

INT4 Weights

3.4 GB

KV-Cache per Token65536 bytes
Activation Estimate1.00 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

A10Goptimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

240.7 tok/s

Cost/Month

$285

Cost/M Tokens

$0.45

Use this config →
A30optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

374.3 tok/s

Cost/Month

$332

Cost/M Tokens

$0.34

Use this config →
RTX 4090optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

404.4 tok/s

Cost/Month

$370

Cost/M Tokens

$0.35

Use this config →

API Pricing Comparison

ProviderInput $/MOutput $/MBadges
huggingface$0.15$0.15
Cheapest

Quality Benchmarks

MMLU
38.0
HumanEval
35.2
GSM8K
24.0
MT-Bench
55.0

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

vllmsglangtgitensorrt-llmollama

Supported Precisions

BF16 (default)FP8INT4

Similar Models