Devstral 2 (123B) on Intel Xeon Silver (4100 to 4300 series) NAS (256 GB)

Can the Intel Xeon Silver (4100 to 4300 series) NAS (256 GB) run Devstral 2 (123B)?

Barely: it runs very slowly

Very slow. At Q8_0 it needs about 155 GB of 230 GB usable, with an estimated speed of 0.3 tok/s.

Best quant: Q8_0
Generation speed: 0.3 tok/s
Prompt processing: 2.8 tok/s
First token (1K prompt): 365.8 s
Largest safe context: 213K

Best app to run it on the Intel Xeon Silver (4100 to 4300 series) NAS (256 GB)

On Linux

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

One command with Ollama’s own build of this model.
Serves an OpenAI-compatible API that other apps and coding tools can use.

ollama run devstral-2:123b-instruct-2512-q8_0

llama.cpp Usually the first to support new model architectures.
KoboldCpp

Want an agent? Devstral 2 (123B) supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

Reverse engineering? Serve Devstral 2 (123B) locally and use it from Ghidra, IDA Pro, Binary Ninja, radare2 or JADX with one of these:

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 Devstral 2 (123B)

Recommended for the Intel Xeon Silver (4100 to 4300 series) NAS (256 GB): Q8_0. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run devstral-2:123b-instruct-2512-q8_0

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q8_0 files (opens in a new tab)

huggingface.co/unsloth/Devstral-2-123B-Instruct-2512-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Devstral-2-123B-Instruct-2512-GGUF

Original weights · Hugging Face

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

huggingface.co/mistralai/Devstral-2-123B-Instruct-2512 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Mistral AI. The weights themselves download from Hugging Face.

github.com/mistralai/mistral-inference (opens in a new tab)

Mistral AI’s official inference code.

git clone https://github.com/mistralai/mistral-inference

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

How it’s rated

Quality 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (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 Very slow: How well it runs on the Intel Xeon Silver (4100 to 4300 series) NAS (256 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.	38.7 / 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.	1.3 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Match score	80.0 / 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 Silver (4100 to 4300 series) NAS (256 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	72.0 GB	230 GB	0.9 tok/s	Very slow	60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	83.2 GB	230 GB	0.7 tok/s	Very slow	72Great quality (A) · 72 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q4_K_M`	98.3 GB	230 GB	0.5 tok/s	Very slow	81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q5_K_M`	111 GB	230 GB	0.5 tok/s	Very slow	83Great quality (A) · 83 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q6_K`	125 GB	230 GB	0.4 tok/s	Very slow	85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q8_0`	155 GB	230 GB	0.3 tok/s	Very slow	86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`F16`	272 GB	230 GB	—	Won't run	86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab) 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

81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q4_K_M · 17.6 tok/s · Runs well (tight fit)
60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) Q2_K · 11.1 tok/s · Runs well
60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (256 GB) Q2_K · 11.4 tok/s · Runs well
60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (512 GB) Q2_K · 11.4 tok/s · Runs well
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA B200 Q8_0 · 40.0 tok/s · Runs great
83Great quality (A) · 83 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H200 141GB SXM Q5_K_M · 38.9 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.