Can the AMD Radeon PRO W7900 run LFM2 24B-A2B?

Yes, it runs great

Runs great. At Q8_0 it needs about 28.4 GB of 48.0 GB usable, with an estimated speed of 114 tok/s.

Best quant: Q8_0
Generation speed: 114 tok/s
Prompt processing: 33,049 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 125K

Best app to run it on the AMD Radeon PRO W7900

On Windows

Lemonade

Desktop app · runs on llama.cpp, ONNX Runtime GenAI (Ryzen AI NPU)

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

lemonade pull LiquidAI/LFM2-24B-A2B-GGUF:Q8_0

LM Studio Point-and-click: search, download and chat in one window.
Ollama One command with Ollama’s own build of this model.

On Linux

Lemonade

Desktop app · runs on llama.cpp, ONNX Runtime GenAI (Ryzen AI NPU)

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

lemonade pull LiquidAI/LFM2-24B-A2B-GGUF:Q8_0

LM Studio Point-and-click: search, download and chat in one window.
Ollama One command with Ollama’s own build of this model.

Want an agent? LFM2 24B-A2B 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 24B-A2B

Recommended for the AMD Radeon PRO W7900: Q8_0. 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 lfm2:24b-q8_0

Quantized files · GGUF

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

Download the Q8_0 file (opens in a new tab)

huggingface.co/LiquidAI/LFM2-24B-A2B-GGUF (opens in a new tab)

ollama run hf.co/LiquidAI/LFM2-24B-A2B-GGUF:Q8_0

Original weights · Hugging Face

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

huggingface.co/LiquidAI/LFM2-24B-A2B (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 56Good quality (B) · 56 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.: How capable the model itself is at Q8_0, 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 AMD Radeon PRO W7900: 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.	25.2 / 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.	13.7 / 15
Match score	78.9 / 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 AMD Radeon PRO W7900

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	12.7 GB	48.0 GB	215 tok/s	Runs great	39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q3_K_M`	14.8 GB	48.0 GB	193 tok/s	Runs great	47Fair quality (C) · 47 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q4_K_M`	17.7 GB	48.0 GB	170 tok/s	Runs great	53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	20.1 GB	48.0 GB	153 tok/s	Runs great	54Fair quality (C) · 54 of 100: how capable the model is at Q5_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)
`Q6_K`	22.7 GB	48.0 GB	138 tok/s	Runs great	55Good quality (B) · 55 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	28.4 GB	48.0 GB	114 tok/s	Runs great	56Good quality (B) · 56 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.	GGUF (opens in a new tab)
`F16`	50.8 GB	48.0 GB	46.2 tok/s	Runs welloffloads to RAM	56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (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

56Good quality (B) · 56 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Pro (48 GB) Q8_0 · 51.4 tok/s · Runs great
55Good quality (B) · 55 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q6_K · 195 tok/s · Runs great
56Good quality (B) · 56 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Apple M1 Max (64 GB) Q8_0 · 69.0 tok/s · Runs great
56Good quality (B) · 56 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q8_0 · 86.0 tok/s · Runs great
54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q5_K_M · 160 tok/s · Runs great
54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q5_K_M · 169 tok/s · Runs great

Quick answers

How much memory does LFM2 24B-A2B need on the PRO W7900 48GB?

At Q8_0 it needs about 28.4 GB. The PRO W7900 48GB has 48.0 GB usable.

How fast is LFM2 24B-A2B on the PRO W7900 48GB?

About 114 tok/s at Q8_0, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of LFM2 24B-A2B should I use on the PRO W7900 48GB?

Q8_0. 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.