Updated minutes ago
MPT 30B
MosaicML · dense · 30B parameters · 8,192 context
Quality48.0
Architecture Details
TypeDENSE
Total Parameters30B
Active Parameters30B
Layers48
Hidden Dimension7,168
Attention Heads64
KV Heads8
Head Dimension112
Vocab Size50,432
Memory Requirements
BF16 Weights
60.0 GB
FP8 Weights
30.0 GB
INT4 Weights
15.0 GB
KV-Cache per Token344064 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
H20optimal
FP8 · 1 GPU · tensorrt-llm
100/100
score
Throughput
1.0K tok/s
Cost/Month
$940
Cost/M Tokens
$0.36
H200 SXMoptimal
FP8 · 1 GPU · tensorrt-llm
95/100
score
Throughput
1.1K tok/s
Cost/Month
$2553
Cost/M Tokens
$0.93
H100 SXMoptimal
FP8 · 1 GPU · tensorrt-llm
95/100
score
Throughput
840.8 tok/s
Cost/Month
$1794
Cost/M Tokens
$0.81
API Pricing Comparison
No API pricing data available for this model.
Quality Benchmarks
MMLU56.0
HumanEval28.0
GSM8K40.0
MT-Bench68.0
Capabilities
Features
✗ Tool Use✗ Vision✓ Code✗ Math✗ Reasoning✗ Multilingual✗ Structured Output
Supported Frameworks
vllmtgi
Supported Precisions
BF16 (default)FP8INT4