Hunyuan A13B (80B-A13B) on Apple M2 Max (96 GB)

Can the Apple M2 Max (96 GB) run Hunyuan A13B (80B-A13B)?

Yes, it runs well

Runs well. At Q4_K_M it needs about 56.5 GB of 72.0 GB usable, with an estimated speed of 29.3 tok/s.

Best quant: Q4_K_M
Generation speed: 29.3 tok/s
Prompt processing: 649 tok/s
First token (1K prompt): 1.6 s
Largest safe context: 32K

Best app to run it on the Apple M2 Max (96 GB)

On macOS

LM Studio

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

Runs the MLX build, typically 10–20% faster than GGUF for a model with 13B active parameters on Apple silicon.
Point-and-click: search, download and chat in one window.

Open Hunyuan A13B (80B-A13B) in LM Studio

llama.cpp Usually the first to support new model architectures.
MLX LM Runs the MLX build, typically 10–20% faster than GGUF for a model with 13B active parameters on Apple silicon.

Want an agent? Hunyuan A13B (80B-A13B) 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 Hunyuan A13B (80B-A13B)

Recommended for the Apple M2 Max (96 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 file (opens in a new tab)

huggingface.co/tencent/Hunyuan-A13B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/tencent/Hunyuan-A13B-Instruct-GGUF:Q4_K_M

Original weights · Hugging Face

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

huggingface.co/tencent/Hunyuan-A13B-Instruct (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/Tencent-Hunyuan/Hunyuan-A13B (opens in a new tab)

git clone https://github.com/Tencent-Hunyuan/Hunyuan-A13B

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

How it’s rated

Quality 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (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 Runs well: How well it runs on the Apple M2 Max (96 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.	31.6 / 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.	12.8 / 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	84.5 / 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 Max (96 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	39.6 GB	72.0 GB	45.8 tok/s	Runs great	51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q3_K_M`	46.8 GB	72.0 GB	37.0 tok/s	Runs great	62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q4_K_M`	56.5 GB	72.0 GB	29.3 tok/s	Runs well	70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	64.5 GB	72.0 GB	24.6 tok/s	Runs welltight fit	71Great quality (A) · 71 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q6_K`	73.4 GB	72.0 GB	17.7 tok/s	Runs wellover GPU memory limit	73Great quality (A) · 73 of 100: how capable the model is at Q6_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)
`Q8_0`	92.6 GB	72.0 GB	—	Won't run	74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · part 1 of 2 (opens in a new tab)
`F16`	168 GB	72.0 GB	—	Won't run	74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 9/100 (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

73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q6_K · 82.5 tok/s · Runs great
73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) Q6_K · 38.8 tok/s · Runs great
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (128 GB) Q4_K_M · 38.6 tok/s · Runs great
73Great quality (A) · 73 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. Apple M3 Ultra (256 GB) Q6_K · 39.6 tok/s · Runs great
62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q3_K_M · 48.4 tok/s · Runs well (tight fit)
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX Spark N1X (6144-core GPU) (128 GB) Q4_K_M · 25.9 tok/s · Runs well

Quick answers

How much memory does Hunyuan A13B (80B-A13B) need on the M2 Max 96GB?

At Q4_K_M it needs about 56.5 GB. The M2 Max 96GB has 72.0 GB usable.

How fast is Hunyuan A13B (80B-A13B) on the M2 Max 96GB?

About 29.3 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Hunyuan A13B (80B-A13B) should I use on the M2 Max 96GB?

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.