Can the Intel Arc B580 run LFM2.5 8B-A1B?

Yes, it runs great

Runs great. At Q6_K it needs about 8.2 GB of 12.0 GB usable, with an estimated speed of 115 tok/s.

Best quant: Q6_K
Generation speed: 115 tok/s
Prompt processing: 10,010 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 125K

Best app to run it on the Intel Arc B580

On Windows

Command line + local API · runs on llama.cpp

Supports Intel Arc through SYCL and Vulkan.
Usually the first to support new model architectures.

llama-server -hf LiquidAI/LFM2.5-8B-A1B-GGUF:Q6_K

LM Studio Point-and-click: search, download and chat in one window.
Ollama Intel GPU support here is experimental (Vulkan).

On Linux

llama.cpp

Command line + local API · runs on llama.cpp

Supports Intel Arc through SYCL and Vulkan.
Usually the first to support new model architectures.

llama-server -hf LiquidAI/LFM2.5-8B-A1B-GGUF:Q6_K

LM Studio Point-and-click: search, download and chat in one window.
Ollama Intel GPU support here is experimental (Vulkan).

Want an agent? LFM2.5 8B-A1B supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

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 LFM2.5 8B-A1B

Recommended for the Intel Arc B580: 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.

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

ollama run lfm2.5:8b

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/LiquidAI/LFM2.5-8B-A1B-GGUF (opens in a new tab)

ollama run hf.co/LiquidAI/LFM2.5-8B-A1B-GGUF:Q6_K

Original weights · Hugging Face

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

huggingface.co/LiquidAI/LFM2.5-8B-A1B (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/Liquid4All/cookbook (opens in a new tab)

Liquid AI’s official cookbook for running LFM models.

git clone https://github.com/Liquid4All/cookbook

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 51Fair quality (C) · 51 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q6_K, 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 great: How well it runs on the Intel Arc B580: 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.	23.2 / 45
Memory fitFull marks when everything sits in GPU 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
Match score	78.2 / 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 B580

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	4.7 GB	12.0 GB	190 tok/s	Runs great	36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q3_K_M`	5.5 GB	12.0 GB	168 tok/s	Runs great	43Fair quality (C) · 43 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q4_K_M`	6.5 GB	12.0 GB	145 tok/s	Runs great	49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	7.3 GB	12.0 GB	129 tok/s	Runs great	50Fair quality (C) · 50 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	8.2 GB	12.0 GB	115 tok/s	Runs great	51Fair quality (C) · 51 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	10.3 GB	12.0 GB	93.5 tok/s	Runs welltight fit	52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	18.2 GB	12.0 GB	23.5 tok/s	Slowheavy RAM offload	52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (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

52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX F16 · 93.7 tok/s · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q8_0 · 123 tok/s · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Pro (24 GB) Q8_0 · 71.4 tok/s · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 F16 · 101 tok/s · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 Ti 16GB Q8_0 · 82.4 tok/s · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q8_0 · 136 tok/s · Runs great

Quick answers

How much memory does LFM2.5 8B-A1B need on the Arc B580 12GB?

At Q6_K it needs about 8.2 GB. The Arc B580 12GB has 12.0 GB usable.

How fast is LFM2.5 8B-A1B on the Arc B580 12GB?

About 115 tok/s at Q6_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of LFM2.5 8B-A1B should I use on the Arc B580 12GB?

Q6_K. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

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.