- input
- $0.00
- output
- $0.00
- Context
- 33Ktokens
- Listed
- 2mo ago
- Size
- 0.6Bparameters
Cost/1M tokens
How it compares
Frequently asked questions
Running locally
By our estimate, Qwen3 Reranker 0.6B needs about 0.9 GB at Q4, 1.2 GB at Q8 and 1.9 GB at FP16 of VRAM. That covers the weights plus headroom for a short context, and longer contexts need more.
Yes, by our estimates Qwen3 Reranker 0.6B fits on an 8 GB GPU at FP16 (about 1.9 GB) and at higher precision on larger cards.
Yes, a Mac with at least 8 GB of unified memory should run Qwen3 Reranker 0.6B at Q4, which needs an estimated 0.9 GB. This assumes macOS gives the GPU about 75% of unified memory.
API and pricing
Yes, PrimeIntellect lists a free Qwen3 Reranker 0.6B endpoint at $0 per 1M input and output tokens. Free endpoints often have tighter rate limits.
1 of 1 tracked Qwen3 Reranker 0.6B endpoints had 99% uptime or better over the last day. The best was PrimeIntellect at 100.0%.
Privacy and data
PrimeIntellect offers zero data retention for Qwen3 Reranker 0.6B, so prompts are not stored after the request.
Yes, Qwen3 Reranker 0.6B has open weights, so you can run it on your own hardware and keep prompts on your own machines.
Capabilities and specs
Qwen3 Reranker 0.6B has a 33K token context window.
No, Qwen3 Reranker 0.6B takes text input only.
Quality and benchmarks
Similar models from other labs include Nemotron 3.5 Rerank 8B (NVIDIA), rerank-2.5-lite (VoyageAI by MongoDB) and rerank-2.5 (VoyageAI by MongoDB). They are the closest matches by kind and release date.
Nemotron 3.5 Rerank 8BQwen3 Reranker 0.6B vs Nemotron 3.5 Rerank 8Brerank-2.5-liteQwen3 Reranker 0.6B vs rerank-2.5-litererank-2.5Qwen3 Reranker 0.6B vs rerank-2.5
Versions and lineage
Both have a 33K token context window.
Licensing and access
Qwen3 Reranker 0.6B has open weights, so you can download and run it yourself.
The Qwen3 Reranker 0.6B weights are on Hugging Face at Qwen/Qwen3-Reranker-0.6B.
Basics
Qwen3 Reranker 0.6B was made by Qwen. It was first listed on OpenRouter on August 26, 2026.
Yes, PrimeIntellect offers a free Qwen3 Reranker 0.6B API endpoint. Its weights are also open, so you can run it on your own hardware without API fees.
Generated from Vertical Tabs data, updated November 12, 2026.




Discussion
No comments yet
Be the first to share your thoughts.