Decision models ·

Qwen3 Reranker 8B

Task
Reranking search results
Returns
Probability or score
Precision tier
90 / 100
Size
8.2B
Max input
32K tokens
License
apache-2.0
Released
2025-06

What it decides

Returns
A relevance score (probability of “yes”) for each query and document pair.
Checks
Query and document pairs, code
Languages
100+ languages
Precision
90 / 100 · MTEB-R 69.0, MMTEB-R 72.9, MTEB-Code 81.2 (model card).
Clarity
Probability or score (15 of 15 clarity points)
How it runs
Scores query and document pairs · a small language model, so it runs in the same apps as LLMs.
License
apache-2.0 (Open (Apache, MIT))

Source: model card on Hugging Face (opens in a new tab) · How decision models are rated

How to run it

Quantized files · GGUF

Works in llama.cpp (llama-server --rerank), Lemonade and other llama.cpp servers with a rerank endpoint. No sign-in needed.

huggingface.co/mradermacher/Qwen3-Reranker-8B-GGUF (opens in a new tab)

llama-server -hf mradermacher/Qwen3-Reranker-8B-GGUF --rerank

Original weights · Hugging Face

Full-precision files from Alibaba, for Transformers, Sentence Transformers, Text Embeddings Inference, Infinity or vLLM.

huggingface.co/Qwen/Qwen3-Reranker-8B (opens in a new tab)

No sign-in needed.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

Apps that run Qwen3 Reranker 8B

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or Mac in the Model Finder for an exact answer.

Mac (Apple silicon)

llama.cpp

Serves the GGUF build behind a /v1/rerank endpoint with llama-server --rerank.

Also good: Sentence Transformers, Lemonade

Windows PC, NVIDIA GPU

llama.cpp

Serves the GGUF build behind a /v1/rerank endpoint with llama-server --rerank.

Also good: Sentence Transformers, Lemonade

Windows PC, AMD Radeon

llama.cpp

Serves the GGUF build behind a /v1/rerank endpoint with llama-server --rerank.

Also good: Lemonade, Sentence Transformers

Linux, NVIDIA GPU

llama.cpp

Serves the GGUF build behind a /v1/rerank endpoint with llama-server --rerank.

Also good: vLLM, Sentence Transformers

Linux server, 80 GB+ GPUs

llama.cpp

Serves the GGUF build behind a /v1/rerank endpoint with llama-server --rerank.

Also good: vLLM, SGLang

App Type Opens it as Systems Engine Start
llama.cpp CLI + API GGUF macOSWindowsLinux llama.cpp 
llama-server -hf mradermacher/Qwen3-Reranker-8B-GGUF:Q4_K_M --rerank
vLLM Server Original weights WSLWindowsLinux vLLM 
vllm serve Qwen/Qwen3-Reranker-8B
SGLang Server Original weights WSLWindowsLinux SGLang 
python3 -m sglang.launch_server --model-path Qwen/Qwen3-Reranker-8B
Lemonade Desktop app GGUF macOSWindowsLinux llama.cpp, ONNX Runtime GenAI 
lemonade pull mradermacher/Qwen3-Reranker-8B-GGUF:Q4_K_M
Sentence Transformers Library Original weights macOSWindowsLinux PyTorch Get Sentence Transformers

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory and speed

Each quantization on an NVIDIA GeForce RTX 4090, for one decision on a 512-token input. The best hardware table below covers other GPUs and Macs.

Format Memory needed Time per decision Decisions per second Quality Download
Q4_K_M 5.9 GB 81 ms 12/s 85Excellent quality (S) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q5_K_M 6.7 GB 83 ms 12/s 87Excellent quality (S) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q6_K 7.6 GB 84 ms 12/s 89Excellent quality (S) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q8_0 9.6 GB 88 ms 11/s 90Excellent quality (S) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
F16 17.3 GB 103 ms 9.7/s 90Excellent quality (S) · 90 of 100: how capable the model is at F16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab) Original weights (opens in a new tab)

One request at a time. Servers that batch (Text Embeddings Inference, vLLM, Infinity) handle many more decisions per second.

Best hardware for Qwen3 Reranker 8B

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A580 (launch price $179) at Q4_K_M.

Quality Hardware Quant Memory Time per decision Runs
90Excellent quality (S) · 90 of 100: how capable the model is at F16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Sapphire NITRO+ AMD Radeon RX 7900 XTX Vapor-X 24GBAMD Radeon RX 7900 XTX F16 18.5 GB / 24.0 GB 93 ms Runs great
90Excellent quality (S) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Sapphire NITRO+ AMD Radeon RX 9070 XT OCAMD Radeon RX 9070 XT Q8_0 10.4 GB / 16.0 GB 97 ms Runs great
90Excellent quality (S) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Founders EditionNVIDIA GeForce RTX 4090 Q8_0 10.8 GB / 24.0 GB 88 ms Runs great
90Excellent quality (S) · 90 of 100: how capable the model is at F16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Founders EditionNVIDIA GeForce RTX 5090 F16 18.9 GB / 32.0 GB 75 ms Runs great
90Excellent quality (S) · 90 of 100: how capable the model is at F16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Workstation EditionNVIDIA RTX PRO 6000 Blackwell F16 22.1 GB / 96.0 GB 66 ms Runs great
90Excellent quality (S) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 Founders EditionNVIDIA GeForce RTX 5080 Q8_0 10.4 GB / 16.0 GB 121 ms Runs great
90Excellent quality (S) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPERNVIDIA GeForce RTX 4080 SUPER Q8_0 10.4 GB / 16.0 GB 133 ms Runs well
90Excellent quality (S) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. ASUS TUF Gaming GeForce RTX 5070 Ti 16GB GDDR7 OC EditionNVIDIA GeForce RTX 5070 Ti Q8_0 10.4 GB / 16.0 GB 151 ms Runs well
90Excellent quality (S) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPERNVIDIA GeForce RTX 4070 Ti SUPER Q8_0 10.4 GB / 16.0 GB 156 ms Runs well
89Excellent quality (S) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Framework DesktopAMD Ryzen AI Max+ 395 (128 GB) Q6_K 15.3 GB / 96.0 GB 161 ms Runs well

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.