Hunyuan 1.8B Instruct on Apple M2 Max (96 GB)

Can the Apple M2 Max (96 GB) run Hunyuan 1.8B Instruct?

Yes, it runs great

Runs great. At F16 it needs about 10.5 GB of 72.0 GB usable, with an estimated speed of 55.4 tok/s.

Best quant: F16
Generation speed: 55.4 tok/s
Prompt processing: 4,711 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 256K

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 35–90% faster than GGUF for a model with 1.8B active parameters on Apple silicon.
Point-and-click: search, download and chat in one window.

Open Hunyuan 1.8B Instruct in LM Studio

MLX LM Runs the MLX build, typically 35–90% faster than GGUF for a model with 1.8B active parameters on Apple silicon.
Unsloth Desktop Runs the MLX build, typically 35–90% faster than GGUF for a model with 1.8B 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 Hunyuan 1.8B Instruct

Recommended for the Apple M2 Max (96 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/bartowski/tencent_Hunyuan-1.8B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/bartowski/tencent_Hunyuan-1.8B-Instruct-GGUF:BF16

Original weights · Hugging Face

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

huggingface.co/tencent/Hunyuan-1.8B-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-7B (opens in a new tab)

git clone https://github.com/Tencent-Hunyuan/Hunyuan-7B

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

How it’s rated

Quality 22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (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 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.	9.9 / 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.	3.4 / 15
Match score	53.3 / 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 M2 Max (96 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	7.6 GB	72.0 GB	388 tok/s	Runs great	15Basic quality (D) · 15 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	7.8 GB	72.0 GB	305 tok/s	Runs great	18Basic quality (D) · 18 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	8.0 GB	72.0 GB	236 tok/s	Runs great	20Basic quality (D) · 20 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	8.2 GB	72.0 GB	195 tok/s	Runs great	21Basic quality (D) · 21 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	8.4 GB	72.0 GB	164 tok/s	Runs great	21Basic quality (D) · 21 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	8.8 GB	72.0 GB	120 tok/s	Runs great	22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	10.5 GB	72.0 GB	55.4 tok/s	Runs great	22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (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

22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 F16 · 43.8 tok/s · Runs great
22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 F16 · 56.0 tok/s · Runs great
22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3060 12GB F16 · 57.9 tok/s · Runs great
22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER F16 · 81.1 tok/s · Runs great
22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT F16 · 88.7 tok/s · Runs great
22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 Ti 16GB F16 · 46.3 tok/s · Runs great

Quick answers

How much memory does Hunyuan 1.8B Instruct need on the M2 Max 96GB?

At F16 it needs about 10.5 GB. The M2 Max 96GB has 72.0 GB usable.

How fast is Hunyuan 1.8B Instruct on the M2 Max 96GB?

About 55.4 tok/s at F16, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Hunyuan 1.8B Instruct should I use on the M2 Max 96GB?

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.