Updated minutes ago
Qwen 2.5 32B
Alibaba · dense · 32.5B parameters · 131,072 context
Quality81.0
Architecture Details
TypeDENSE
Total Parameters32.5B
Active Parameters32.5B
Layers64
Hidden Dimension5,120
Attention Heads40
KV Heads8
Head Dimension128
Vocab Size152,064
Memory Requirements
BF16 Weights
65.0 GB
FP8 Weights
32.5 GB
INT4 Weights
16.3 GB
KV-Cache per Token262144 bytes
Activation Estimate2.00 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
H20optimal
FP8 · 1 GPU · tensorrt-llm
100/100
score
Throughput
1.0K tok/s
Cost/Month
$940
Cost/M Tokens
$0.35
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
862.3 tok/s
Cost/Month
$1794
Cost/M Tokens
$0.79
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| alibaba | $0.80 | $0.80 | Cheapest |
| together | $0.80 | $0.80 |
Quality Benchmarks
MMLU83.0
HumanEval54.0
GSM8K90.0
MT-Bench84.0
Capabilities
Features
✓ Tool Use✗ Vision✓ Code✓ Math✗ Reasoning✓ Multilingual✓ Structured Output
Supported Frameworks
vllmsglangtgitensorrt-llm
Supported Precisions
BF16 (default)FP8INT4