on

Can the Apple M5 Ultra (512 GB) run Tülu 3 405B?

72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.

Yes, but slowly

Slow. At Q4_K_M it needs about 283 GB of 384 GB usable, with an estimated speed of 3.1 tok/s.

Best quant
Q4_K_M
Generation speed
3.1 tok/s
Prompt processing
57.6 tok/s
First token (1K prompt)
17.8 s
Largest safe context
128K

Best app to run it on the Apple M5 Ultra (512 GB)

On macOS

LM Studio

Desktop app · runs on llama.cpp, MLX

  • Point-and-click: search, download and chat in one window.

Open Tülu 3 405B in LM Studio

  • llama.cpp Usually the first to support new model architectures.
  • Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

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 Tülu 3 405B

Recommended for the Apple M5 Ultra (512 GB): Q4_K_M. 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 Q4_K_M files (opens in a new tab)

huggingface.co/bartowski/Llama-3.1-Tulu-3-405B-GGUF (opens in a new tab)

ollama run hf.co/bartowski/Llama-3.1-Tulu-3-405B-GGUF

Original weights · Hugging Face

Full-precision files from Ai2, for fine-tuning, vLLM, Transformers.

huggingface.co/allenai/Llama-3.1-Tulu-3-405B (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 72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q4_K_M, 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 Slow
How well it runs on the Apple M5 Ultra (512 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.32.5 / 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.4.2 / 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 score76.7 / 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 (512 GB)

Quant Memory needed Available Speed Runs Quality Download
Q2_K 198 GB 384 GB 5.1 tok/s Slow 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
Q3_K_M 234 GB 384 GB 4.0 tok/s Slow 63Good quality (B) · 63 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 · folder (opens in a new tab)
Q4_K_M 283 GB 384 GB 3.1 tok/s Slow 72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
Q5_K_M 324 GB 384 GB 2.6 tok/s Very slow 73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
Q6_K 368 GB 384 GB 2.2 tok/s Very slowtight fit 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
Q8_0 466 GB 384 GB 1.4 tok/s Very slowfar over GPU memory limit 76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
F16 847 GB 384 GB — Won't run 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 10/100 (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

Quick answers

How much memory does Tülu 3 405B need on the M5 Ultra 512GB?

At Q4_K_M it needs about 283 GB. The M5 Ultra 512GB has 384 GB usable.

How fast is Tülu 3 405B on the M5 Ultra 512GB?

About 3.1 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Tülu 3 405B should I use on the M5 Ultra 512GB?

Q4_K_M. 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.

Was this page helpful?