Updated minutes ago
Vicuna 7B
LMSYS · dense · 7B parameters · 4,096 context
Quality50.0
Architecture Details
TypeDENSE
Total Parameters7B
Active Parameters7B
Layers32
Hidden Dimension4,096
Attention Heads32
KV Heads32
Head Dimension128
Vocab Size32,000
Memory Requirements
BF16 Weights
14.0 GB
FP8 Weights
7.0 GB
INT4 Weights
3.5 GB
KV-Cache per Token524288 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
231.4 tok/s
Cost/Month
$285
Cost/M Tokens
$0.47
A30optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
359.9 tok/s
Cost/Month
$332
Cost/M Tokens
$0.35
RTX 4090optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
388.8 tok/s
Cost/Month
$370
Cost/M Tokens
$0.36
API Pricing Comparison
No API pricing data available for this model.
Capabilities
Features
✗ Tool Use✗ Vision✓ Code✗ Math✗ Reasoning✗ Multilingual✗ Structured Output
Supported Frameworks
vllmsglangtgiollama
Supported Precisions
BF16 (default)FP8INT4