Updated minutes ago
CodeGemma 7B
Google · dense · 8.5B parameters · 8,192 context
Quality52.0
Architecture Details
TypeDENSE
Total Parameters8.5B
Active Parameters8.5B
Layers28
Hidden Dimension3,072
Attention Heads16
KV Heads16
Head Dimension256
Vocab Size256,128
Memory Requirements
BF16 Weights
17.0 GB
FP8 Weights
8.5 GB
INT4 Weights
4.3 GB
KV-Cache per Token229376 bytes
Activation Estimate0.80 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
A30optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
266.7 tok/s
Cost/Month
$332
Cost/M Tokens
$0.47
RTX 4090optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
288.2 tok/s
Cost/Month
$370
Cost/M Tokens
$0.49
RTX 3090optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
267.6 tok/s
Cost/Month
$180
Cost/M Tokens
$0.26
API Pricing Comparison
No API pricing data available for this model.
Quality Benchmarks
MMLU56.0
HumanEval44.0
GSM8K50.0
MT-Bench68.0
Capabilities
Features
✗ Tool Use✗ Vision✓ Code✓ Math✗ Reasoning✗ Multilingual✗ Structured Output
Supported Frameworks
vllmsglangtgiollama
Supported Precisions
BF16 (default)FP8INT4