Trinity Mini (26B-A3B) on AMD Ryzen AI Max+ 395 (64 GB)

Can the AMD Ryzen AI Max+ 395 (64 GB) run Trinity Mini (26B-A3B)?

Yes, it runs great

Runs great. At Q8_0 it needs about 32.3 GB of 48.0 GB usable, with an estimated speed of 39.1 tok/s.

Best quant: Q8_0
Generation speed: 39.1 tok/s
Prompt processing: 12,276 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 128K

Best app to run it on the AMD Ryzen AI Max+ 395 (64 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 arcee-ai/Trinity-Mini-GGUF:Q8_0

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 arcee-ai/Trinity-Mini-GGUF:Q8_0

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

Want an agent? Trinity Mini (26B-A3B) 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 Trinity Mini (26B-A3B)

Recommended for the AMD Ryzen AI Max+ 395 (64 GB): Q8_0. 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 Q8_0 file (opens in a new tab)

huggingface.co/arcee-ai/Trinity-Mini-GGUF (opens in a new tab)

ollama run hf.co/arcee-ai/Trinity-Mini-GGUF:Q8_0

Original weights · Hugging Face

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

huggingface.co/arcee-ai/Trinity-Mini (opens in a new tab)

No sign-in needed.

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

How it’s rated

Quality 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (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 Ryzen AI Max+ 395 (64 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.	29.7 / 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.	14.8 / 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	84.5 / 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 AMD Ryzen AI Max+ 395 (64 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	15.1 GB	48.0 GB	101 tok/s	Runs great	46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	17.4 GB	48.0 GB	84.6 tok/s	Runs great	55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	20.5 GB	48.0 GB	69.2 tok/s	Runs great	62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	23.2 GB	48.0 GB	59.1 tok/s	Runs great	64Good quality (B) · 64 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.	GGUF (opens in a new tab)
`Q6_K`	26.0 GB	48.0 GB	51.1 tok/s	Runs great	65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	32.3 GB	48.0 GB	39.1 tok/s	Runs great	66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	56.8 GB	48.0 GB	16.5 tok/s	Slowfar over GPU memory limit	66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.	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

66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Apple M1 Max (64 GB) Q8_0 · 56.4 tok/s · Runs great
66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q8_0 · 71.4 tok/s · Runs great
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Pro (48 GB) Q6_K · 53.8 tok/s · Runs great
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q6_K · 179 tok/s · Runs great
66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell F16 · 98.2 tok/s · Runs great
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q6_K · 127 tok/s · Runs well (tight fit)

Quick answers

How much memory does Trinity Mini (26B-A3B) need on the AMD Ryzen AI Max+ 395 64GB?

At Q8_0 it needs about 32.3 GB. The AMD Ryzen AI Max+ 395 64GB has 48.0 GB usable.

How fast is Trinity Mini (26B-A3B) on the AMD Ryzen AI Max+ 395 64GB?

About 39.1 tok/s at Q8_0, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Trinity Mini (26B-A3B) should I use on the AMD Ryzen AI Max+ 395 64GB?

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.