on

Can the Apple M2 Ultra (192 GB) run InternVL3 78B?

70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs well

Runs well. At Q4_K_M it needs about 62.6 GB of 144 GB usable, with an estimated speed of 10.8 tok/s.

Best quant
Q4_K_M
Generation speed
10.8 tok/s
Prompt processing
215 tok/s
First token (1K prompt)
4.8 s
Largest safe context
32K

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 78.4B active parameters on Apple silicon.
  • Point-and-click: search, download and chat in one window.

Open InternVL3 78B 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 InternVL3 78B

Recommended for the Apple M2 Ultra (192 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/unsloth/InternVL3-78B-GGUF (opens in a new tab)

ollama run hf.co/unsloth/InternVL3-78B-GGUF:Q4_K_M

Original weights · Hugging Face

Full-precision files from Shanghai AI Lab, for fine-tuning, vLLM, Transformers.

huggingface.co/OpenGVLab/InternVL3-78B (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 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (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 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.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.7.8 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.10.0 / 15
Match score74.5 / 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 46.2 GB 144 GB 17.7 tok/s Runs well 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q3_K_M 53.2 GB 144 GB 13.9 tok/s Runs well 62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q4_K_M 62.6 GB 144 GB 10.8 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 74/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q5_K_M 70.5 GB 144 GB 8.9 tok/s Slow 71Great quality (A) · 71 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
Q6_K 79.1 GB 144 GB 7.5 tok/s Slow 73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
Q8_0 97.9 GB 144 GB 5.5 tok/s Slow 74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. GGUF (UD-Q8_K_XL) · folder (opens in a new tab)
F16 172 GB 144 GB 2.2 tok/s Very slowfar over GPU memory limit 74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (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

Quick answers

How much memory does InternVL3 78B need on the M2 Ultra 192GB?

At Q4_K_M it needs about 62.6 GB. The M2 Ultra 192GB has 144 GB usable.

How fast is InternVL3 78B on the M2 Ultra 192GB?

About 10.8 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of InternVL3 78B should I use on the M2 Ultra 192GB?

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?