Updated minutes ago
MPT 7B
MosaicML · dense · 6.7B parameters · 65,536 context
Quality36.0
Architecture Details
TypeDENSE
Total Parameters6.7B
Active Parameters6.7B
Layers32
Hidden Dimension4,096
Attention Heads32
KV Heads32
Head Dimension128
Vocab Size50,432
Memory Requirements
BF16 Weights
13.4 GB
FP8 Weights
6.7 GB
INT4 Weights
3.4 GB
KV-Cache per Token262144 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
A10Goptimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
241.8 tok/s
Cost/Month
$285
Cost/M Tokens
$0.45
A30optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
376.0 tok/s
Cost/Month
$332
Cost/M Tokens
$0.34
RTX 4090optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
406.2 tok/s
Cost/Month
$370
Cost/M Tokens
$0.35
API Pricing Comparison
No API pricing data available for this model.
Quality Benchmarks
MMLU42.0
HumanEval18.0
GSM8K28.0
MT-Bench60.0
Capabilities
Features
✗ Tool Use✗ Vision✓ Code✗ Math✗ Reasoning✗ Multilingual✗ Structured Output
Supported Frameworks
vllmtgiollama
Supported Precisions
BF16 (default)FP8INT4