RecurrentGemma 9B IT on Intel Xeon W-2100 series NAS (32 GB)

Can the Intel Xeon W-2100 series NAS (32 GB) run RecurrentGemma 9B IT?

Yes, it runs well

Runs well. At Q2_K it needs about 6.7 GB of 26.2 GB usable, with an estimated speed of 11.2 tok/s.

Best quant: Q2_K
Generation speed: 11.2 tok/s
Prompt processing: 37.4 tok/s
First token (1K prompt): 27.4 s
Largest safe context: 8K

Download RecurrentGemma 9B IT

Original weights · Hugging Face

Full-precision files from Google, for fine-tuning, vLLM, Transformers.

huggingface.co/google/recurrentgemma-9b-it (opens in a new tab)

Free Hugging Face account needed: request access on the model page, and Google approves it (usually within minutes to a few hours).

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

How it’s rated

Quality 23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q2_K, 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 Intel Xeon W-2100 series NAS (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.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	10.7 / 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
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	7.9 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	5.9 / 15
Match score	49.5 / 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 Intel Xeon W-2100 series NAS (32 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	6.7 GB	26.2 GB	11.2 tok/s	Runs well	23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q3_K_M`	7.5 GB	26.2 GB	8.8 tok/s	Slow	28Basic quality (D) · 28 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q4_K_M`	8.7 GB	26.2 GB	6.8 tok/s	Slow	32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q5_K_M`	9.6 GB	26.2 GB	5.6 tok/s	Slow	32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q6_K`	10.7 GB	26.2 GB	4.7 tok/s	Slow	33Basic quality (D) · 33 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q8_0`	13.0 GB	26.2 GB	3.5 tok/s	Slow	34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`F16`	22.1 GB	26.2 GB	1.6 tok/s	Very slow	34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q8_0 · 43.6 tok/s · Runs great
34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q8_0 · 47.8 tok/s · Runs great
34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti Q8_0 · 58.1 tok/s · Runs great
34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 Q8_0 · 62.3 tok/s · Runs great
34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 F16 · 53.6 tok/s · Runs great
33Basic quality (D) · 33 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER Q6_K · 44.6 tok/s · 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.