Check my GPU

on

Can the AMD Radeon RX 9070 XT run Kimi-VL A3B Instruct?

76 ptsGreat (A) · 76 of 100 points: Model quality 21.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15

Yes, it runs well

Runs well. At Q5_K_M it needs about 13.3 GB of 16.0 GB usable, with an estimated speed of 93.1 tok/s.

Best quant
Q5_K_M
Generation speed
93.1 tok/s
Prompt processing
20,109 tok/s
First token (1K prompt)
0.3 s
Largest safe context
92K

Download Kimi-VL A3B Instruct

Recommended for the AMD Radeon RX 9070 XT: Q5_K_M. Every other quantization has its own download link in the table below.

Quantized files · GGUF

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

Download the Q5_K_M file (opens in a new tab)

huggingface.co/mradermacher/Kimi-VL-A3B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/Kimi-VL-A3B-Instruct-GGUF:Q5_K_M

Original weights · Hugging Face

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

huggingface.co/moonshotai/Kimi-VL-A3B-Instruct (opens in a new tab)

No sign-in needed.

Links checked 5 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.21.8 / 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.15.0 / 15
Total76.8 / 10076 ptsGreat (A) · 76 of 100 points: Model quality 21.8/45, 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 AMD Radeon RX 9070 XT

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 8.2 GB 16.0 GB 185 tok/s Runs well 67 ptsGood (B) · 67 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.9/15 GGUF (opens in a new tab)
Q3_K_M 9.7 GB 16.0 GB 146 tok/s Runs well 72 ptsGreat (A) · 72 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.0/15 GGUF (opens in a new tab)
Q4_K_M 11.7 GB 16.0 GB 113 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q5_K_M 13.3 GB 16.0 GB 93.1 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 21.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q6_K 15.1 GB 16.0 GB 78.2 tok/s Tight fit 76 ptsGreat (A) · 76 of 100 points: Model quality 22.3/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q8_0 19.0 GB 16.0 GB 25.2 tok/s Runs with offload 59 ptsGood (B) · 59 of 100 points: Model quality 22.5/45, Memory fit 10.0/25, Speed 11.9/15, Memory use 15.0/15 GGUF (opens in a new tab)
F16 34.5 GB 16.0 GB 5.2 tok/s Heavy offload 46 ptsUsable (C) · 46 of 100 points: Model quality 22.5/45, Memory fit 4.0/25, Speed 5.4/15, Memory use 15.0/15 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.