LFM2.5 1.2B Instruct on AMD Ryzen AI Max 385 (32 GB)

Can the AMD Ryzen AI Max 385 (32 GB) run LFM2.5 1.2B Instruct?

Yes, it runs great

Runs great. At F16 it needs about 5.0 GB of 24.0 GB usable, with an estimated speed of 54.3 tok/s.

Best quant: F16
Generation speed: 54.3 tok/s
Prompt processing: 24,323 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 125K

Best app to run it on the AMD Ryzen AI Max 385 (32 GB)

On Windows

Lemonade

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

Built for Ryzen AI and Strix Halo, including NPU + iGPU modes on Windows.

lemonade pull LiquidAI/LFM2.5-1.2B-Instruct-GGUF:BF16

LM Studio Point-and-click: search, download and chat in one window.
llama.cpp Usually the first to support new model architectures.

On Linux

Lemonade

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

Built for Ryzen AI and Strix Halo, including NPU + iGPU modes on Windows.

lemonade pull LiquidAI/LFM2.5-1.2B-Instruct-GGUF:BF16

LM Studio Point-and-click: search, download and chat in one window.
llama.cpp Usually the first to support new model architectures.

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 1.2B Instruct

Recommended for the AMD Ryzen AI Max 385 (32 GB): F16. 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 F16 file (opens in a new tab)

huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/LiquidAI/LFM2.5-1.2B-Instruct-GGUF:BF16

Original weights · Hugging Face

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

huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct (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 1 day ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at F16, 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 Ryzen AI Max 385 (32 GB): 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.	14.4 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	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.	4.8 / 15
Match score	59.2 / 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 AMD Ryzen AI Max 385 (32 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	3.1 GB	24.0 GB	380 tok/s	Runs great	22Basic quality (D) · 22 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q3_K_M`	3.2 GB	24.0 GB	299 tok/s	Runs great	26Basic quality (D) · 26 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q4_K_M`	3.3 GB	24.0 GB	231 tok/s	Runs great	30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	3.5 GB	24.0 GB	191 tok/s	Runs great	31Basic quality (D) · 31 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`	3.6 GB	24.0 GB	160 tok/s	Runs great	31Basic quality (D) · 31 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	3.9 GB	24.0 GB	118 tok/s	Runs great	32Basic quality (D) · 32 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	5.0 GB	24.0 GB	54.3 tok/s	Runs great	32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (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

32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 F16 · 67.0 tok/s · Runs great
32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 F16 · 85.7 tok/s · Runs great
32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3060 12GB F16 · 88.6 tok/s · Runs great
32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER F16 · 124 tok/s · Runs great
32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Pro (24 GB) F16 · 57.9 tok/s · Runs great
32Basic quality (D) · 32 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 (16 GB) Q8_0 · 55.2 tok/s · Runs great

Quick answers

How much memory does LFM2.5 1.2B Instruct need on the AMD Ryzen AI Max 385 32GB?

At F16 it needs about 5.0 GB. The AMD Ryzen AI Max 385 32GB has 24.0 GB usable.

How fast is LFM2.5 1.2B Instruct on the AMD Ryzen AI Max 385 32GB?

About 54.3 tok/s at F16, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of LFM2.5 1.2B Instruct should I use on the AMD Ryzen AI Max 385 32GB?

F16. 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.