DiffusionGemma 26B-A4B IT on Apple M5 Ultra (256 GB)

Can the Apple M5 Ultra (256 GB) run DiffusionGemma 26B-A4B IT?

Yes, it runs great

Runs great. At F16 it needs about 68.0 GB of 192 GB usable, with an estimated speed of 56.1 tok/s.

Best quant: F16
Generation speed: 56.1 tok/s
Prompt processing: 5,844 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 256K

Best app to run it on the Apple M5 Ultra (256 GB)

On macOS

LM Studio

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

Runs the MLX build, typically 35–90% faster than GGUF for a model with 4B active parameters on Apple silicon.
Point-and-click: search, download and chat in one window.

Open DiffusionGemma 26B-A4B IT in LM Studio

MLX LM Runs the MLX build, typically 35–90% faster than GGUF for a model with 4B active parameters on Apple silicon.
Unsloth Desktop Runs the MLX build, typically 35–90% faster than GGUF for a model with 4B active parameters on Apple silicon.

Want an agent? DiffusionGemma 26B-A4B IT 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 DiffusionGemma 26B-A4B IT

Recommended for the Apple M5 Ultra (256 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/unsloth/diffusiongemma-26B-A4B-it-GGUF (opens in a new tab)

ollama run hf.co/unsloth/diffusiongemma-26B-A4B-it-GGUF:BF16

Original weights · Hugging Face

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

huggingface.co/google/diffusiongemma-26B-A4B-it (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 78Great quality (A) · 78 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.: 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 M5 Ultra (256 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.	35.1 / 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.	8.2 / 15
Match score	83.3 / 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 Apple M5 Ultra (256 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	26.7 GB	192 GB	198 tok/s	Runs great	54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q3_K_M`	29.0 GB	192 GB	176 tok/s	Runs great	65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q4_K_M`	32.1 GB	192 GB	153 tok/s	Runs great	74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	34.7 GB	192 GB	137 tok/s	Runs great	75Great quality (A) · 75 of 100: how capable the model is at Q5_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)
`Q6_K`	37.5 GB	192 GB	123 tok/s	Runs great	77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	43.7 GB	192 GB	100 tok/s	Runs great	78Great quality (A) · 78 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.	GGUF (opens in a new tab)
`F16`	68.0 GB	192 GB	56.1 tok/s	Runs great	78Great quality (A) · 78 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.	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

78Great quality (A) · 78 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. Apple M1 Max (64 GB) Q8_0 · 44.7 tok/s · Runs great
78Great quality (A) · 78 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. Apple M4 Max (64 GB) Q8_0 · 57.4 tok/s · Runs great
77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Pro (48 GB) Q6_K · 42.4 tok/s · Runs great
77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q6_K · 161 tok/s · Runs great
78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell F16 · 82.5 tok/s · Runs great
77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q6_K · 108 tok/s · Runs well (tight fit)

Quick answers

How much memory does DiffusionGemma 26B-A4B IT need on the M5 Ultra 256GB?

At F16 it needs about 68.0 GB. The M5 Ultra 256GB has 192 GB usable.

How fast is DiffusionGemma 26B-A4B IT on the M5 Ultra 256GB?

About 56.1 tok/s at F16, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of DiffusionGemma 26B-A4B IT should I use on the M5 Ultra 256GB?

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.