Updated minutes ago
Qwen 1.5 MoE A2.7B
Alibaba · moe · 14.3B parameters · 32,768 context
Quality50.0
Architecture Details
TypeMOE
Total Parameters14.3B
Active Parameters2.7B
Layers24
Hidden Dimension2,048
Attention Heads16
KV Heads16
Head Dimension128
Vocab Size151,936
Total Experts60
Active Experts4
Memory Requirements
BF16 Weights
28.6 GB
FP8 Weights
14.3 GB
INT4 Weights
7.2 GB
KV-Cache per Token196608 bytes
Activation Estimate0.50 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
A100 40GB SXMoptimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
1.1K tok/s
Cost/Month
$807
Cost/M Tokens
$0.29
RTX A6000optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
768.0 tok/s
Cost/Month
$465
Cost/M Tokens
$0.23
A40optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
696.0 tok/s
Cost/Month
$399
Cost/M Tokens
$0.22
API Pricing Comparison
No API pricing data available for this model.
Capabilities
Features
✗ Tool Use✗ Vision✓ Code✓ Math✗ Reasoning✓ Multilingual✓ Structured Output
Supported Frameworks
vllmsglangtgi
Supported Precisions
BF16 (default)FP8INT4