Updated minutes ago
Qwen 2.5 3B
Alibaba · dense · 3.09B parameters · 32,768 context
Quality58.0
Architecture Details
TypeDENSE
Total Parameters3.09B
Active Parameters3.09B
Layers36
Hidden Dimension2,048
Attention Heads16
KV Heads2
Head Dimension128
Vocab Size152,064
Memory Requirements
BF16 Weights
6.2 GB
FP8 Weights
3.1 GB
INT4 Weights
1.5 GB
KV-Cache per Token36864 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
RTX 4070 Tioptimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
440.4 tok/s
Cost/Month
$237
Cost/M Tokens
$0.21
RTX 3080optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
664.0 tok/s
Cost/Month
$133
Cost/M Tokens
$0.08
RTX 4070 Superoptimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
440.4 tok/s
Cost/Month
$209
Cost/M Tokens
$0.18
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| alibaba | $0.10 | $0.10 | Cheapest |
Quality Benchmarks
MMLU65.0
HumanEval35.0
GSM8K70.0
MT-Bench72.0
Capabilities
Features
✓ Tool Use✗ Vision✓ Code✓ Math✗ Reasoning✓ Multilingual✓ Structured Output
Supported Frameworks
vllmsglangtgiollama
Supported Precisions
BF16 (default)FP8INT4