Can the Apple M3 Pro (18 GB) run Qwen3.5 27B?

Yes, but slowly (over GPU memory limit)

Slow (over GPU memory limit). At Q2_K it needs about 13.2 GB of 12.1 GB usable, with an estimated speed of 8.0 tok/s.

Best quant: Q2_K
Generation speed: 8.0 tok/s
Prompt processing: 165 tok/s
First token (1K prompt): 6.2 s
Largest safe context: —

Best app to run it on the Apple M3 Pro (18 GB)

On macOS

LM Studio

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

Splits the model between GPU memory and system RAM, which this setup needs.
Point-and-click: search, download and chat in one window.

Open Qwen3.5 27B in LM Studio

Ollama Splits the model between GPU memory and system RAM, which this setup needs.
llama.cpp Splits the model between GPU memory and system RAM, which this setup needs.

Reverse engineering? Serve Qwen3.5 27B locally and use it from Ghidra, IDA Pro, Binary Ninja, radare2 or JADX with one of these:

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 27B

Recommended for the Apple M3 Pro (18 GB): Q2_K. 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 qwen3.5:27b

Quantized files · GGUF

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

Download the Q2_K (UD-Q2_K_XL) file (opens in a new tab)

huggingface.co/unsloth/Qwen3.5-27B-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Qwen3.5-27B-GGUF:UD-Q2_K_XL

Original weights · Hugging Face

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

huggingface.co/Qwen/Qwen3.5-27B (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 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q2_K, 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 Slowover GPU memory limit: How well it runs on the Apple M3 Pro (18 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.	29.3 / 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.	10.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	6.7 / 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	61.0 / 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 M3 Pro (18 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	13.2 GB	12.1 GB	8.0 tok/s	Slowover GPU memory limit	65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (UD-Q2_K_XL) (opens in a new tab)
`Q3_K_M`	15.7 GB	12.1 GB	—	Won't run	78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	19.0 GB	12.1 GB	—	Won't run	88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	21.8 GB	12.1 GB	—	Won't run	90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	24.9 GB	12.1 GB	—	Won't run	92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	31.5 GB	12.1 GB	—	Won't run	93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	57.7 GB	12.1 GB	—	Won't run	93Excellent quality (A+) · 93 of 100: how capable the model is at F16, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (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

92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q6_K · 54.9 tok/s · Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q4_K_M · 41.4 tok/s · Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q4_K_M · 44.5 tok/s · Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q4_K_M · 36.5 tok/s · Runs great
93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q8_0 · 40.3 tok/s · Runs great
78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q3_K_M · 42.0 tok/s · Runs well (tight fit)

Quick answers

How much memory does Qwen3.5 27B need on the M3 Pro 18GB?

At Q2_K it needs about 13.2 GB. The M3 Pro 18GB has 12.1 GB usable.

How fast is Qwen3.5 27B on the M3 Pro 18GB?

About 8.0 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Qwen3.5 27B should I use on the M3 Pro 18GB?

Q2_K. 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.