Qwen 2.5 1.5B
Alibaba · dense · 1.5B parameters · 32,768 context
Parameters
1.5B
Context Window
32K tokens
Architecture
Dense
Best GPU
A4000
Intelligence Brief
Qwen 2.5 1.5B is a 1.5B parameter DENSE model from Alibaba, featuring Grouped Query Attention (GQA) with 28 layers and 1,536 hidden dimensions. With a 32,768 token context window, it supports structured output, code, math, multilingual. For self-hosted inference, A4000 delivers optimal throughput at $161/month.
Recent changes
Loading…
Related models
5 suggestions- Qwen 2.5 14BQwen 2.5 · 14.8B$0.300/M out
- Qwen 2.5 32BQwen 2.5 · 32.5B$0.800/M out
- Qwen 2.5 3BQwen 2.5 · 3.09B$0.100/M out
- Qwen 2.5 Coder 32BQwen 2.5 · 32.5Bfree/M out
- Qwen 2.5 0.5BQwen 2.5 · 0.5B—
Picks: same family first, then same vendor within ±2× params, then top tag-overlap matches. Price shown is the cheapest Output $/M across providers — the row's page shows the canonical anchor.
Architecture Details
Memory Requirements
BF16 Weights
3.0 GB
FP8 Weights
1.5 GB
INT4 Weights
0.8 GB
GPU Compatibility Matrix
Qwen 2.5 1.5B is compatible with 100% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
BF16 · 1 GPU · vllm
90/100
score
Throughput
806.4 tok/s
Latency (ITL)
1.2ms
Est. TTFT
0ms
Cost/Month
$161
Cost/M Tokens
$0.08
BF16 · 1 GPU · vllm
90/100
score
Throughput
1.3K tok/s
Latency (ITL)
0.8ms
Est. TTFT
0ms
Cost/Month
$304
Cost/M Tokens
$0.09
BF16 · 1 GPU · vllm
90/100
score
Throughput
907.1 tok/s
Latency (ITL)
1.1ms
Est. TTFT
0ms
Cost/Month
$237
Cost/M Tokens
$0.10
Deployment Options
API Deployment
No API pricing available
Single GPU
A4000
$161/mo
Min VRAM: 2 GB
Multi-GPU
A4000
806.4 tok/s
Best available config
API Pricing Comparison
No API pricing data available for this model.
Performance Estimates
Throughput by GPU
VRAM Breakdown (A4000, BF16)
Precision Impact
bf16
3.0 GB
weights/GPU
~806.4 tok/s
fp8
1.5 GB
weights/GPU
int4
0.8 GB
weights/GPU
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy Qwen 2.5 1.5B
Self-Hosted Infrastructure
Similar Models
Qwen 2.5 0.5B
0.5B params · dense
Quality: 50
Qwen 2.5 3B
3.09B params · dense
Quality: 58
from $0.10/M
DeepSeek R1 Distill 1.5B
1.5B params · dense
Quality: 42
Qwen 2.5 Coder 1.5B
1.5B params · dense
Quality: 40
Whisper Large V3
1.55B params · dense
Quality: 50
from $0.01/M
Frequently Asked Questions
How much VRAM does Qwen 2.5 1.5B need for inference?
Qwen 2.5 1.5B requires approximately 3.0 GB of VRAM at BF16 precision, 1.5 GB at FP8, or 0.8 GB at INT4 quantization. Additional VRAM is needed for KV-cache (28672 bytes per token) and activations (~0.30 GB).
What is the best GPU for Qwen 2.5 1.5B?
The top recommended GPU for Qwen 2.5 1.5B is the A4000 using BF16 precision. It achieves approximately 806.4 tokens/sec at an estimated cost of $161/month ($0.08/M tokens). Score: 90/100.
How much does Qwen 2.5 1.5B inference cost?
Qwen 2.5 1.5B inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.