Devstral Small 2 (24B) on NVIDIA GeForce RTX 5090

Can the NVIDIA GeForce RTX 5090 run Devstral Small 2 (24B)?

88 pts

Yes, it runs well

Runs well. At Q6_K it needs about 23.2 GB of 32.0 GB usable, with an estimated speed of 63.6 tok/s.

Best quant: Q6_K
Generation speed: 63.6 tok/s
Prompt processing: 3,143 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 60K

Download Devstral Small 2 (24B)

Recommended for the NVIDIA GeForce RTX 5090: Q6_K. 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.

ollama run devstral-small-2:24b

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

Quantized files · GGUF

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

Download the Q6_K file (opens in a new tab)

huggingface.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF:Q6_K

Original weights · Hugging Face

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

huggingface.co/mistralai/Devstral-Small-2-24B-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)

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

Mistral AI’s official inference code.

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

How the S grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	33.9 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 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
Total	88.9 / 100	88 ptsExcellent (S) · 88 of 100 points: Model quality 33.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every quantization on the NVIDIA GeForce RTX 5090

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	13.1 GB	32.0 GB	150 tok/s	Runs well	73 ptsGreat (A) · 73 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.5/15	GGUF (opens in a new tab)
`Q3_K_M`	15.3 GB	32.0 GB	118 tok/s	Runs well	79 ptsGreat (A) · 79 of 100 points: Model quality 28.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.0/15	GGUF (opens in a new tab)
`Q4_K_M`	18.2 GB	32.0 GB	91.6 tok/s	Runs well	85 ptsExcellent (S) · 85 of 100 points: Model quality 32.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.1/15	GGUF (opens in a new tab)
`Q5_K_M`	20.6 GB	32.0 GB	75.7 tok/s	Runs well	88 ptsExcellent (S) · 88 of 100 points: Model quality 33.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.8/15	GGUF (opens in a new tab)
`Q6_K`	23.2 GB	32.0 GB	63.6 tok/s	Runs well	88 ptsExcellent (S) · 88 of 100 points: Model quality 33.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q8_0`	29.0 GB	32.0 GB	46.6 tok/s	Tight fit	88 ptsExcellent (S) · 88 of 100 points: Model quality 34.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	GGUF (opens in a new tab)
`F16`	51.6 GB	32.0 GB	1.9 tok/s	Heavy offload	56 ptsUsable (C) · 56 of 100 points: Model quality 34.2/45, Memory fit 4.0/25, Speed 3.2/15, Memory use 15.0/15	GGUF (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

88 ptsExcellent (S) · 88 of 100 points: Model quality 33.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 Q5_K_M · 42.6 tok/s
88 ptsExcellent (S) · 88 of 100 points: Model quality 33.2/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 Q5_K_M · 39.5 tok/s
87 ptsExcellent (S) · 87 of 100 points: Model quality 32.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX Q4_K_M · 42.3 tok/s
82 ptsGreat (A) · 82 of 100 points: Model quality 28.7/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 Ti SUPER Q3_K_M · 44.4 tok/s
82 ptsGreat (A) · 82 of 100 points: Model quality 28.7/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4080 SUPER Q3_K_M · 48.6 tok/s

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.