Phi-4 Reasoning Plus (14B) on Intel Arc A580

Can the Intel Arc A580 run Phi-4 Reasoning Plus (14B)?

Yes, it runs well (offloads to RAM)

Runs well (offloads to RAM). At Q3_K_M it needs about 9.9 GB of 8.0 GB usable, with an estimated speed of 18.7 tok/s.

Best quant: Q3_K_M
Generation speed: 18.7 tok/s
Prompt processing: 756 tok/s
First token (1K prompt): 1.4 s
Largest safe context: —

Best app to run it on the Intel Arc A580

On Windows

llama.cpp

Command line + local API · runs on llama.cpp

Splits the model between GPU memory and system RAM, which this setup needs.
Gives you direct control of how many layers sit on the GPU, the best way to squeeze a model that doesn’t quite fit.
Supports Intel Arc through SYCL and Vulkan.

llama-server -hf unsloth/Phi-4-reasoning-plus-GGUF:Q3_K_M

LM Studio Splits the model between GPU memory and system RAM, which this setup needs.
Ollama Splits the model between GPU memory and system RAM, which this setup needs.

On Linux

llama.cpp

Command line + local API · runs on llama.cpp

Splits the model between GPU memory and system RAM, which this setup needs.
Gives you direct control of how many layers sit on the GPU, the best way to squeeze a model that doesn’t quite fit.
Supports Intel Arc through SYCL and Vulkan.

llama-server -hf unsloth/Phi-4-reasoning-plus-GGUF:Q3_K_M

LM Studio Splits the model between GPU memory and system RAM, which this setup needs.
Ollama Splits the model between GPU memory and system RAM, which this setup needs.

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Phi-4 Reasoning Plus (14B)

Recommended for the Intel Arc A580: 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.

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

ollama run phi4-reasoning:plus

Quantized files · GGUF

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

Download the Q3_K_M file (opens in a new tab)

huggingface.co/unsloth/Phi-4-reasoning-plus-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Phi-4-reasoning-plus-GGUF:Q3_K_M

Original weights · Hugging Face

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

huggingface.co/microsoft/Phi-4-reasoning-plus (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)

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

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

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

How it’s rated

Quality 60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q3_K_M, 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 Runs welloffloads to RAM: How well it runs on the Intel Arc A580: 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.	27.2 / 45
Memory fitFull marks when everything sits in GPU 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.	10.3 / 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	62.5 / 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 Arc A580

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	8.5 GB	8.0 GB	37.1 tok/s	Runs welloffloads to RAM	50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	9.9 GB	8.0 GB	18.7 tok/s	Runs welloffloads to RAM	60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	11.6 GB	8.0 GB	11.0 tok/s	Slowheavy RAM offload	68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	13.1 GB	8.0 GB	8.0 tok/s	Slowheavy RAM offload	69Good quality (B) · 69 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	14.7 GB	8.0 GB	6.1 tok/s	Slowheavy RAM offload	71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	18.2 GB	8.0 GB	4.0 tok/s	Slowheavy RAM offload	72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	32.0 GB	8.0 GB	—	Won't run	72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	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

72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q8_0 · 43.0 tok/s · Runs great
72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q8_0 · 39.9 tok/s · Runs great
71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q6_K · 48.0 tok/s · Runs great
69Good quality (B) · 69 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q5_K_M · 46.5 tok/s · Runs great
69Good quality (B) · 69 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q5_K_M · 50.9 tok/s · Runs great
69Good quality (B) · 69 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti Q5_K_M · 62.0 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.