Can the Apple M2 Ultra (128 GB) run Qwen3.5 4B?

Yes, it runs great

Runs great. At F16 it needs about 17.9 GB of 96.0 GB usable, with an estimated speed of 42.6 tok/s.

Best quant: F16
Generation speed: 42.6 tok/s
Prompt processing: 3,619 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 256K

Best app to run it on the Apple M2 Ultra (128 GB)

On macOS

LM Studio

Desktop app · runs on llama.cpp, MLX · use the MLX build

Runs the MLX build, typically 20–35% faster than GGUF for a model with 4.7B active parameters on Apple silicon.
Point-and-click: search, download and chat in one window.

Open Qwen3.5 4B in LM Studio

Ollama One command with Ollama’s own build of this model.
MLX LM Runs the MLX build, typically 20–35% faster than GGUF for a model with 4.7B active parameters on Apple silicon.

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 Qwen3.5 4B

Recommended for the Apple M2 Ultra (128 GB): F16. 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 qwen3.5:4b-bf16

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/unsloth/Qwen3.5-4B-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Qwen3.5-4B-GGUF:BF16

Original weights · Hugging Face

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

huggingface.co/Qwen/Qwen3.5-4B (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 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (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 Apple M2 Ultra (128 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.	27.9 / 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.	4.3 / 15
Match score	72.2 / 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 Apple M2 Ultra (128 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	10.4 GB	96.0 GB	298 tok/s	Runs great	43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (UD-Q2_K_XL) (opens in a new tab)
`Q3_K_M`	10.8 GB	96.0 GB	235 tok/s	Runs great	52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	11.4 GB	96.0 GB	181 tok/s	Runs great	58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	11.9 GB	96.0 GB	150 tok/s	Runs great	60Good quality (B) · 60 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	12.4 GB	96.0 GB	126 tok/s	Runs great	61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	13.5 GB	96.0 GB	92.4 tok/s	Runs great	62Good quality (B) · 62 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	17.9 GB	96.0 GB	42.6 tok/s	Runs great	62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (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

62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER F16 · 41.5 tok/s · Runs great
62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER F16 · 45.5 tok/s · Runs great
62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti F16 · 55.4 tok/s · Runs great
62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 F16 · 59.3 tok/s · Runs great
61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 Q6_K · 49.7 tok/s · Runs great
62Good quality (B) · 62 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. Intel Arc B580 Q8_0 · 46.7 tok/s · Runs great

Quick answers

How much memory does Qwen3.5 4B need on the M2 Ultra 128GB?

At F16 it needs about 17.9 GB. The M2 Ultra 128GB has 96.0 GB usable.

How fast is Qwen3.5 4B on the M2 Ultra 128GB?

About 42.6 tok/s at F16, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Qwen3.5 4B should I use on the M2 Ultra 128GB?

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.