BGE Reranker v2 M3 on Intel Xeon W-2100 series NAS (128 GB)

Can the Intel Xeon W-2100 series NAS (128 GB) run BGE Reranker v2 M3?

Yes, but slowly

Slow. At Q8_0 it needs about 1.3 GB of 113 GB usable and makes one decision in about 885 ms.

Best precision: Q8_0
Time per decision: 885 ms
Decisions per second: 1.1/s
Input assumed: 512 tokens
Returns: Probability or score

Best app to run it on the Intel Xeon W-2100 series NAS (128 GB)

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 gpustack/bge-reranker-v2-m3-GGUF:Q8_0 --rerank

Text Embeddings Inference Purpose-built server for encoder rerankers and classifiers: batching and Flash Attention keep each call to milliseconds.
Infinity Local API for rerankers and classifiers, including models TEI does not support.

How we choose: the files published for this model, which apps run in a container on a NAS without a graphics card (models run on its processor), and whether the model fits fully in the memory models can use. Details.

Download BGE Reranker v2 M3

Recommended for the Intel Xeon W-2100 series NAS (128 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/gpustack/bge-reranker-v2-m3-GGUF (opens in a new tab)

llama-server -hf gpustack/bge-reranker-v2-m3-GGUF:Q8_0 --rerank

Original weights · Hugging Face

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

huggingface.co/BAAI/bge-reranker-v2-m3 (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 72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (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 Slow: How well it runs on the Intel Xeon W-2100 series NAS (128 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.	32.4 / 45
Memory fitFull marks when the model fits in the share of the NAS’s memory that models can use (the rest stays with the NAS system and its storage services); 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.	5.0 / 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 score	77.4 / 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 Intel Xeon W-2100 series NAS (128 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q8_0`	1.3 GB	113 GB	885 ms	Slow	72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	1.9 GB	113 GB	1.0 s	Slow	72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 77/100 (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. Batching servers process many requests at once.

Other hardware that runs it

72Great quality (A) · 72 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. AMD Radeon RX 7900 XTX F16 · 8.8 ms · Runs great
72Great quality (A) · 72 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. AMD Radeon RX 9070 XT F16 · 10 ms · Runs great
72Great quality (A) · 72 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. AMD Ryzen AI Max+ 395 (128 GB) F16 · 14 ms · Runs great
72Great quality (A) · 72 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. Apple M1 Max (64 GB) F16 · 61 ms · Runs great
72Great quality (A) · 72 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. Apple M2 Ultra (192 GB) F16 · 26 ms · Runs great
72Great quality (A) · 72 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. Apple M3 Ultra (256 GB) F16 · 25 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.