on

Can the NVIDIA GeForce RTX 5090 run Qwen3 Reranker 8B?

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.

Yes, it runs great

Runs great. At F16 it needs about 18.9 GB of 32.0 GB usable and makes one decision in about 75 ms.

Best quant
F16
Time per decision
75 ms
Decisions per second
13/s
Input assumed
512 tokens
Returns
Probability or score

Best app to run it on the NVIDIA GeForce RTX 5090

On Windows

llama.cpp

Command line + local API · runs on llama.cpp

  • Serves the GGUF build behind a /v1/rerank endpoint with llama-server --rerank.
llama-server -hf mradermacher/Qwen3-Reranker-8B-GGUF:F16 --rerank
  • Sentence Transformers A few lines of Python with Transformers or Sentence Transformers; easiest for scripts and notebooks.
  • Lemonade Serves the GGUF build behind a /v1/rerank endpoint with llama-server --rerank.

On Linux

llama.cpp

Command line + local API · runs on llama.cpp

  • Serves the GGUF build behind a /v1/rerank endpoint with llama-server --rerank.
llama-server -hf mradermacher/Qwen3-Reranker-8B-GGUF:F16 --rerank
  • vLLM Serves the scoring head directly (rerank, classify or reward) with batching.
  • Sentence Transformers A few lines of Python with Transformers or Sentence Transformers; easiest for scripts and notebooks.

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Qwen3 Reranker 8B

Recommended for the NVIDIA GeForce RTX 5090: F16. Every other quantization has its own download link in the table below.

Quantized files · GGUF

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

Download the F16 file (opens in a new tab)

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

llama-server -hf mradermacher/Qwen3-Reranker-8B-GGUF:F16 --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.

How it’s rated

Quality 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.
How capable the model itself is at F16, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: S 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs great
How well it runs on the NVIDIA GeForce RTX 5090: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

PrecisionEditorial precision tier from the model’s published benchmarks, scaled by the quantization or precision used.40.5 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.25.0 / 25
SpeedTime for one decision against a 100 ms target: reading the input plus any tokens the model writes.15.0 / 15
ClarityHow easy the answer is to use in code: a probability or score earns the most, written feedback before a score the least.15.0 / 15
Match score95.5 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the NVIDIA GeForce RTX 5090

Quant Memory needed Available Time per decision Runs Quality Download
Q4_K_M 7.5 GB 32.0 GB 63 ms Runs great 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 8.3 GB 32.0 GB 64 ms Runs great 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 9.2 GB 32.0 GB 65 ms Runs great 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 11.2 GB 32.0 GB 67 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. GGUF (opens in a new tab)
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. GGUF (opens in a new tab) Original weights (opens in a new tab)

Times are for one request with a 512-token input and about 1 tokens written. Batching servers process many requests at once.

Other hardware that runs it

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.