Qwen3 Reranker 0.6B on Raspberry Pi 4 (2 GB)

Can the Raspberry Pi 4 (2 GB) run Qwen3 Reranker 0.6B?

Barely: it runs very slowly (over memory limit)

Very slow (over memory limit). At Q4_K_M it needs about 1.3 GB of 1.2 GB usable and makes one decision in about 10.4 s.

Best quant: Q4_K_M
Time per decision: 10.4 s
Decisions per second: 0.1/s
Input assumed: 512 tokens
Returns: Probability or score

Best app to run it on the Raspberry Pi 4 (2 GB)

On Linux on ARM boards

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 ggml-org/Qwen3-Reranker-0.6B-Q8_0-GGUF:Q4_K_M --rerank

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 0.6B

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/ggml-org/Qwen3-Reranker-0.6B-Q8_0-GGUF (opens in a new tab)

llama-server -hf ggml-org/Qwen3-Reranker-0.6B-Q8_0-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-0.6B (opens in a new tab)

No sign-in needed.

Links checked 1 day ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q4_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 Very slowover memory limit: How well it runs on the Raspberry Pi 4 (2 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.	34.2 / 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.	10.0 / 25
SpeedTime for one decision against a 100 ms target: reading the input plus any tokens the model writes.	1.5 / 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	60.7 / 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 Raspberry Pi 4 (2 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q4_K_M`	1.3 GB	1.2 GB	10.4 s	Very slowover memory limit	76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q5_K_M`	1.4 GB	1.2 GB	10.4 s	Very slowfar over memory limit	77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q6_K`	1.4 GB	1.2 GB	10.4 s	Very slowfar over memory limit	79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q8_0`	1.6 GB	1.2 GB	—	Won't run	80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	2.1 GB	1.2 GB	—	Won't run	80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.	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

80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX F16 · 11 ms · Runs great
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT F16 · 13 ms · Runs great
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. AMD Ryzen AI Max+ 395 (128 GB) F16 · 22 ms · Runs great
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Apple M1 Max (64 GB) F16 · 58 ms · Runs great
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) F16 · 25 ms · Runs great
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (256 GB) F16 · 24 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.