Qwen 3 1.7B
Alibaba · dense · 1.7B parameters · 131,072 context
Parameters
1.7B
Context Window
128K tokens
Architecture
Dense
Best GPU
A4000
Intelligence Brief
Qwen 3 1.7B is a 1.7B parameter DENSE model from Alibaba, featuring Grouped Query Attention (GQA) with 28 layers and 1,536 hidden dimensions. With a 131,072 token context window, it supports tools, structured output, code, math, multilingual, reasoning. For self-hosted inference, A4000 delivers optimal throughput at $161/month.
Recent changes
Loading…
Related models
5 suggestions- Qwen 3 0.6BQwen 3 · 0.6B—
- Qwen 3 235BQwen 3 · 22Bfree/M out
- Qwen 3 30B-A3BQwen 3 · 3.3B$0.450/M out
- Qwen 3 32BQwen 3 · 32.8Bfree/M out
- Qwen 3 4BQwen 3 · 4B$0.100/M out
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
3.4 GB
FP8 Weights
1.7 GB
INT4 Weights
0.8 GB
GPU Compatibility Matrix
Qwen 3 1.7B is compatible with 100% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
BF16 · 1 GPU · vllm
90/100
score
Throughput
711.5 tok/s
Latency (ITL)
1.4ms
Est. TTFT
0ms
Cost/Month
$161
Cost/M Tokens
$0.09
BF16 · 1 GPU · vllm
90/100
score
Throughput
1.1K tok/s
Latency (ITL)
0.9ms
Est. TTFT
0ms
Cost/Month
$304
Cost/M Tokens
$0.10
BF16 · 1 GPU · vllm
90/100
score
Throughput
800.4 tok/s
Latency (ITL)
1.2ms
Est. TTFT
0ms
Cost/Month
$237
Cost/M Tokens
$0.11
Deployment Options
API Deployment
No API pricing available
Single GPU
A4000
$161/mo
Min VRAM: 2 GB
Multi-GPU
A4000
711.5 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
3.4 GB
weights/GPU
~711.5 tok/s
fp8
1.7 GB
weights/GPU
int4
0.8 GB
weights/GPU
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy Qwen 3 1.7B
Self-Hosted Infrastructure
Similar Models
Qwen 3 0.6B
0.6B params · dense
Quality: 50
Qwen 3 4B
4B params · dense
Quality: 57
from $0.10/M
SmolLM2 1.7B
1.7B params · dense
Quality: 50
Whisper Large V3
1.55B params · dense
Quality: 50
from $0.01/M
Moondream 2B
1.86B params · dense
Quality: 50
Frequently Asked Questions
How much VRAM does Qwen 3 1.7B need for inference?
Qwen 3 1.7B requires approximately 3.4 GB of VRAM at BF16 precision, 1.7 GB at FP8, or 0.8 GB at INT4 quantization. Additional VRAM is needed for KV-cache (57344 bytes per token) and activations (~0.30 GB).
What is the best GPU for Qwen 3 1.7B?
The top recommended GPU for Qwen 3 1.7B is the A4000 using BF16 precision. It achieves approximately 711.5 tokens/sec at an estimated cost of $161/month ($0.09/M tokens). Score: 90/100.
How much does Qwen 3 1.7B inference cost?
Qwen 3 1.7B inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.