Qwen3 Reranker 4B on Apple M5 Pro (64 GB)

Can the Apple M5 Pro (64 GB) run Qwen3 Reranker 4B?

Yes, it runs well

Runs well. At Q8_0 it needs about 9.0 GB of 48.0 GB usable and makes one decision in about 381 ms.

Best quant: Q8_0
Time per decision: 381 ms
Decisions per second: 2.6/s
Input assumed: 512 tokens
Returns: Probability or score

Best app to run it on the Apple M5 Pro (64 GB)

On macOS

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-4B-GGUF:Q8_0 --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.

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 4B

Recommended for the Apple M5 Pro (64 GB): Q8_0. 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 Q8_0 file (opens in a new tab)

huggingface.co/mradermacher/Qwen3-Reranker-4B-GGUF (opens in a new tab)

llama-server -hf mradermacher/Qwen3-Reranker-4B-GGUF:Q8_0 --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-4B (opens in a new tab)

No sign-in needed.

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q8_0, 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 Apple M5 Pro (64 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.	40.5 / 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.	7.7 / 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	88.2 / 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 Apple M5 Pro (64 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q4_K_M`	7.2 GB	48.0 GB	370 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`	7.6 GB	48.0 GB	372 ms	Runs well	87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	8.0 GB	48.0 GB	375 ms	Runs well	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`	9.0 GB	48.0 GB	381 ms	Runs well	90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	12.8 GB	48.0 GB	410 ms	Slow	90Excellent quality (A+) · 90 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (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 · 48 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. AMD Radeon RX 9070 XT F16 · 63 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 Ryzen AI Max+ 395 (128 GB) Q8_0 · 89 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 3090 F16 · 99 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 4070 SUPER Q8_0 · 97 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 4070 Ti SUPER F16 · 90 ms · Runs great

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.