Phi-4 (14B) on AMD Radeon RX 9060 XT 8GB

Can the AMD Radeon RX 9060 XT 8GB run Phi-4 (14B)?

58 pts

Yes, with part of the model in system RAM

Runs with offload. At Q3_K_M it needs about 9.9 GB of 8.0 GB usable, with an estimated speed of 16.4 tok/s.

Best quant: Q3_K_M
Generation speed: 16.4 tok/s
Prompt processing: 1,765 tok/s
First token (1K prompt): 0.6 s
Largest safe context: —

Download Phi-4 (14B)

Recommended for the AMD Radeon RX 9060 XT 8GB: Q3_K_M. 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 phi4:14b

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 Q3_K_M (Q3_K_L) file (opens in a new tab)

huggingface.co/microsoft/phi-4-gguf (opens in a new tab)

ollama run hf.co/microsoft/phi-4-gguf:Q3_K_L

Original weights · Hugging Face

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

huggingface.co/microsoft/phi-4 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/microsoft/PhiCookBook (opens in a new tab)

git clone https://github.com/microsoft/PhiCookBook

Microsoft’s official Phi cookbook: setup, inference and fine-tuning guides.

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

How the B 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.	24.2 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	10.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	9.6 / 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	58.8 / 100	58 ptsGood (B) · 58 of 100 points: Model quality 24.2/45, Memory fit 10.0/25, Speed 9.6/15, 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 9060 XT 8GB

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	8.6 GB	8.0 GB	29.1 tok/s	Runs with offload	57 ptsUsable (C) · 57 of 100 points: Model quality 20.2/45, Memory fit 10.0/25, Speed 12.8/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q3_K_M`	9.9 GB	8.0 GB	16.4 tok/s	Runs with offload	58 ptsGood (B) · 58 of 100 points: Model quality 24.2/45, Memory fit 10.0/25, Speed 9.6/15, Memory use 15.0/15	GGUF (Q3_K_L) (opens in a new tab)
`Q4_K_M`	11.6 GB	8.0 GB	10.1 tok/s	Heavy offload	53 ptsUsable (C) · 53 of 100 points: Model quality 27.4/45, Memory fit 4.0/25, Speed 7.5/15, Memory use 15.0/15	GGUF (Q4_K_S) (opens in a new tab)
`Q5_K_M`	13.1 GB	8.0 GB	7.5 tok/s	Heavy offload	53 ptsUsable (C) · 53 of 100 points: Model quality 27.9/45, Memory fit 4.0/25, Speed 6.5/15, Memory use 15.0/15	GGUF (Q5_K_S) (opens in a new tab)
`Q6_K`	14.7 GB	8.0 GB	5.8 tok/s	Heavy offload	53 ptsUsable (C) · 53 of 100 points: Model quality 28.5/45, Memory fit 4.0/25, Speed 5.7/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q8_0`	18.3 GB	8.0 GB	3.8 tok/s	Heavy offload	52 ptsUsable (C) · 52 of 100 points: Model quality 28.8/45, Memory fit 4.0/25, Speed 4.6/15, Memory use 15.0/15	GGUF (opens in a new tab)
`F16`	32.1 GB	8.0 GB	—	Won't run	8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	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

83 ptsGreat (A) · 83 of 100 points: Model quality 28.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 Q8_0 · 42.9 tok/s
83 ptsGreat (A) · 83 of 100 points: Model quality 28.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 Q8_0 · 39.8 tok/s
83 ptsGreat (A) · 83 of 100 points: Model quality 28.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.9/15 AMD Radeon RX 7900 XTX Q6_K · 47.9 tok/s
82 ptsGreat (A) · 82 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 Ti SUPER Q5_K_M · 46.4 tok/s
82 ptsGreat (A) · 82 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4080 SUPER Q5_K_M · 50.8 tok/s
82 ptsGreat (A) · 82 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5070 Ti Q5_K_M · 61.8 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.