ERNIE 4.5 300B-A47B on Apple M2 Ultra (192 GB)

Can the Apple M2 Ultra (192 GB) run ERNIE 4.5 300B-A47B?

Yes, it runs well (tight fit)

Runs well (tight fit). At Q2_K it needs about 134 GB of 144 GB usable, with an estimated speed of 27.1 tok/s.

Best quant: Q2_K
Generation speed: 27.1 tok/s
Prompt processing: 359 tok/s
First token (1K prompt): 2.9 s
Largest safe context: 51K

Best app to run it on the Apple M2 Ultra (192 GB)

On macOS

LM Studio

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

Runs the MLX build, typically up to 10% faster than GGUF for a model with 47B active parameters on Apple silicon.
Point-and-click: search, download and chat in one window.

Open ERNIE 4.5 300B-A47B 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 ERNIE 4.5 300B-A47B

Recommended for the Apple M2 Ultra (192 GB): Q2_K. 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 Q2_K files (opens in a new tab)

huggingface.co/unsloth/ERNIE-4.5-300B-A47B-PT-GGUF (opens in a new tab)

ollama run hf.co/unsloth/ERNIE-4.5-300B-A47B-PT-GGUF

Original weights · Hugging Face

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

huggingface.co/baidu/ERNIE-4.5-300B-A47B-PT (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/PaddlePaddle/ERNIE (opens in a new tab)

git clone https://github.com/PaddlePaddle/ERNIE

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

How it’s rated

Quality 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 76/100 (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 Runs welltight fit: How well it runs on the Apple M2 Ultra (192 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.	25.2 / 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.	24.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	12.3 / 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	76.5 / 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 Ultra (192 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	134 GB	144 GB	27.1 tok/s	Runs welltight fit	56Good quality (B) · 56 of 100: how capable the model is at Q2_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)
`Q3_K_M`	161 GB	144 GB	18.4 tok/s	Slowfar over GPU memory limit	67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q4_K_M`	197 GB	144 GB	—	Won't run	76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q5_K_M`	227 GB	144 GB	—	Won't run	77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q6_K`	260 GB	144 GB	—	Won't run	79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q8_0`	332 GB	144 GB	—	Won't run	80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`F16`	615 GB	144 GB	—	Won't run	80Great quality (A) · 80 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.	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

76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (512 GB) Q4_K_M · 17.3 tok/s · Runs well
67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (256 GB) Q3_K_M · 22.1 tok/s · Runs well (tight fit)
77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI350X Q5_K_M · 97.8 tok/s · Runs great
76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI325X Q4_K_M · 92.8 tok/s · Runs great
76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip Q4_K_M · 114 tok/s · Runs great
67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI300X Q3_K_M · 103 tok/s · Runs great

Quick answers

How much memory does ERNIE 4.5 300B-A47B need on the M2 Ultra 192GB?

At Q2_K it needs about 134 GB. The M2 Ultra 192GB has 144 GB usable.

How fast is ERNIE 4.5 300B-A47B on the M2 Ultra 192GB?

About 27.1 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of ERNIE 4.5 300B-A47B should I use on the M2 Ultra 192GB?

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.