Qwen3.5 2B on AMD Ryzen AI Max+ 395 NAS (64 GB)

Can the AMD Ryzen AI Max+ 395 NAS (64 GB) run Qwen3.5 2B?

Yes, it runs great

Runs great. At Q8_0 it needs about 6.9 GB of 48.0 GB usable, with an estimated speed of 60.7 tok/s.

Best quant: Q8_0
Generation speed: 60.7 tok/s
Prompt processing: 16,224 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 256K

Best app to run it on the AMD Ryzen AI Max+ 395 NAS (64 GB)

On Linux

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

One command with Ollama’s own build of this model.
Serves an OpenAI-compatible API that other apps and coding tools can use.

ollama run qwen3.5:2b-q8_0

llama.cpp Usually the first to support new model architectures.
KoboldCpp

How we choose: the files published for this model, which apps run in a container on a NAS without a graphics card (models run on its processor), and whether the model fits fully in the memory models can use. Details.

Download Qwen3.5 2B

Recommended for the AMD Ryzen AI Max+ 395 NAS (64 GB): 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 qwen3.5:2b-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/unsloth/Qwen3.5-2B-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Qwen3.5-2B-GGUF:Q8_0

Original weights · Hugging Face

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

huggingface.co/Qwen/Qwen3.5-2B (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/QwenLM/Qwen3.8 (opens in a new tab)

Qwen’s current repo: Qwen3.5 and Qwen3.6 redirect here.

git clone https://github.com/QwenLM/Qwen3.8

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

How it’s rated

Quality 40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 61/100 (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 NAS (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.	18.0 / 45
Memory fitFull marks when the model fits in the share of the NAS’s memory that models can use (the rest stays with the NAS system and its storage services); 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.	3.3 / 15
Match score	61.3 / 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 NAS (64 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	5.4 GB	48.0 GB	196 tok/s	Runs great	28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (UD-Q2_K_XL) (opens in a new tab)
`Q3_K_M`	5.7 GB	48.0 GB	154 tok/s	Runs great	33Basic quality (D) · 33 of 100: how capable the model is at Q3_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)
`Q4_K_M`	5.9 GB	48.0 GB	119 tok/s	Runs great	38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	6.2 GB	48.0 GB	98.5 tok/s	Runs great	38Basic quality (D) · 38 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	6.4 GB	48.0 GB	82.7 tok/s	Runs great	39Basic quality (D) · 39 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	6.9 GB	48.0 GB	60.7 tok/s	Runs great	40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	9.1 GB	48.0 GB	28.0 tok/s	Runs well	40Fair quality (C) · 40 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

40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 F16 · 44.2 tok/s · Runs great
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3060 12GB F16 · 45.7 tok/s · Runs great
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER F16 · 63.9 tok/s · Runs great
40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 Q8_0 · 74.9 tok/s · Runs great
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT F16 · 69.9 tok/s · Runs great
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER F16 · 85.3 tok/s · Runs great

Quick answers

How much memory does Qwen3.5 2B need on the AMD Ryzen AI Max+ 395 NAS 64GB?

At Q8_0 it needs about 6.9 GB. The AMD Ryzen AI Max+ 395 NAS 64GB has 48.0 GB usable.

How fast is Qwen3.5 2B on the AMD Ryzen AI Max+ 395 NAS 64GB?

About 60.7 tok/s at Q8_0, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Qwen3.5 2B should I use on the AMD Ryzen AI Max+ 395 NAS 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.