Check my GPU

on

Can the AMD Radeon RX 9070 XT run Ministral 3 3B?

74 ptsGreat (A) · 74 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.4/15

Yes, it runs well

Runs well. At F16 it needs about 10.0 GB of 16.0 GB usable, with an estimated speed of 41.2 tok/s.

Best quant
F16
Generation speed
41.2 tok/s
Prompt processing
15,669 tok/s
First token (1K prompt)
0.3 s
Largest safe context
63K

Download Ministral 3 3B

Recommended for the AMD Radeon RX 9070 XT: F16. 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 ministral-3:3b-instruct-2512-fp16

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 F16 file (opens in a new tab)

huggingface.co/mistralai/Ministral-3-3B-Instruct-2512-GGUF (opens in a new tab)

ollama run hf.co/mistralai/Ministral-3-3B-Instruct-2512-GGUF:BF16

Original weights · Hugging Face

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

huggingface.co/mistralai/Ministral-3-3B-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 6 days ago against Hugging Face, Ollama and GitHub.

How the A 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.19.8 / 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.14.4 / 15
Total74.2 / 10074 ptsGreat (A) · 74 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.4/15

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

Every quantization on the AMD Radeon RX 9070 XT

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 3.8 GB 16.0 GB 289 tok/s Runs well 59 ptsGood (B) · 59 of 100 points: Model quality 13.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.5/15 GGUF files (opens in a new tab)
Q3_K_M 4.2 GB 16.0 GB 227 tok/s Runs well 62 ptsGood (B) · 62 of 100 points: Model quality 16.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.0/15 GGUF files (opens in a new tab)
Q4_K_M 4.6 GB 16.0 GB 176 tok/s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15 GGUF (opens in a new tab)
Q5_K_M 5.0 GB 16.0 GB 145 tok/s Runs well 66 ptsGood (B) · 66 of 100 points: Model quality 19.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15 GGUF (opens in a new tab)
Q6_K 5.4 GB 16.0 GB 122 tok/s Runs well 67 ptsGood (B) · 67 of 100 points: Model quality 19.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.8/15 GGUF files (opens in a new tab)
Q8_0 6.4 GB 16.0 GB 89.5 tok/s Runs well 68 ptsGood (B) · 68 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.2/15 GGUF (opens in a new tab)
F16 10.0 GB 16.0 GB 41.2 tok/s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.4/15 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

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.