Qwen3 Reranker 8B on AMD Ryzen AI 9 HX 370 (DDR5 SO-DIMM) (32 GB)

Can the AMD Ryzen AI 9 HX 370 (DDR5 SO-DIMM) (32 GB) run Qwen3 Reranker 8B?

Yes, it runs well

Runs well. At Q5_K_M it needs about 8.6 GB of 24.0 GB usable and makes one decision in about 393 ms.

Best quant: Q5_K_M
Time per decision: 393 ms
Decisions per second: 2.5/s
Input assumed: 512 tokens
Returns: Probability or score

Best app to run it on the AMD Ryzen AI 9 HX 370 (DDR5 SO-DIMM) (32 GB)

On Windows

Lemonade

Desktop app · runs on llama.cpp, ONNX Runtime GenAI (Ryzen AI NPU)

Serves the GGUF build behind a /v1/rerank endpoint with llama-server --rerank.
Built for Ryzen AI and Strix Halo, including NPU + iGPU modes on Windows.

lemonade pull mradermacher/Qwen3-Reranker-8B-GGUF:Q5_K_M

llama.cpp Serves the GGUF build behind a /v1/rerank endpoint with llama-server --rerank.
Sentence Transformers A few lines of Python with Transformers or Sentence Transformers; easiest for scripts and notebooks.

On Linux

Lemonade

Desktop app · runs on llama.cpp, ONNX Runtime GenAI (Ryzen AI NPU)

Serves the GGUF build behind a /v1/rerank endpoint with llama-server --rerank.
Built for Ryzen AI and Strix Halo, including NPU + iGPU modes on Windows.

lemonade pull mradermacher/Qwen3-Reranker-8B-GGUF:Q5_K_M

llama.cpp Serves the GGUF build behind a /v1/rerank endpoint with llama-server --rerank.
vLLM Serves the scoring head directly (rerank, classify or reward) with batching.

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 AMD Ryzen AI 9 HX 370 (DDR5 SO-DIMM) (32 GB): Q5_K_M. 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 Q5_K_M 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:Q5_K_M --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 87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q5_K_M, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs well: How well it runs on the AMD Ryzen AI 9 HX 370 (DDR5 SO-DIMM) (32 GB): 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.	39.3 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	25.0 / 25
SpeedTime for one decision against a 100 ms target: reading the input plus any tokens the model writes.	7.6 / 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 score	86.9 / 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 AMD Ryzen AI 9 HX 370 (DDR5 SO-DIMM) (32 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q4_K_M`	7.8 GB	24.0 GB	375 ms	Runs well	85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	8.6 GB	24.0 GB	393 ms	Runs well	87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	9.5 GB	24.0 GB	413 ms	Slow	89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	11.5 GB	24.0 GB	458 ms	Slow	90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	19.2 GB	24.0 GB	657 ms	Slow	90Excellent quality (A+) · 90 of 100: how capable the model is at F16, whatever it runs on. Match score 86/100 (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

90Excellent quality (A+) · 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. AMD Radeon RX 7900 XTX F16 · 93 ms · Runs great
90Excellent quality (A+) · 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. AMD Radeon RX 9070 XT Q8_0 · 97 ms · Runs great
90Excellent quality (A+) · 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 Q8_0 · 88 ms · Runs great
90Excellent quality (A+) · 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 F16 · 75 ms · Runs great
90Excellent quality (A+) · 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 F16 · 66 ms · Runs great
90Excellent quality (A+) · 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 Q8_0 · 121 ms · Runs great

Quick answers

How much memory does Qwen3 Reranker 8B need on the AMD Ryzen AI 9 HX 370 (DDR5 SO-DIMM) 32GB?

At Q5_K_M it needs about 8.6 GB. The AMD Ryzen AI 9 HX 370 (DDR5 SO-DIMM) 32GB has 24.0 GB usable.

How fast is Qwen3 Reranker 8B on the AMD Ryzen AI 9 HX 370 (DDR5 SO-DIMM) 32GB?

It makes one decision in about 393 ms at Q5_K_M, an estimate from the hardware and the size of the model.

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.