on

Can the Apple M3 Ultra (512 GB) run K2 Horizon 7B?

80Great quality (A) · 80 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.

Yes, it runs great

Runs great. At Q8_0 it needs about 42.1 GB of 384 GB usable, with an estimated speed of 49.0 tok/s.

Best quant
Q8_0
Generation speed
49.0 tok/s
Prompt processing
1,956 tok/s
First token (1K prompt)
0.5 s
Largest safe context
512K

Best app to run it on the Apple M3 Ultra (512 GB)

On macOS

LM Studio

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

  • Runs the MLX build, typically 20–35% faster than GGUF for a model with 9B active parameters on Apple silicon.
  • Point-and-click: search, download and chat in one window.

Open K2 Horizon 7B in LM Studio

  • MLX LM Runs the MLX build, typically 20–35% faster than GGUF for a model with 9B active parameters on Apple silicon.
  • Jan Runs the MLX build, typically 20–35% faster than GGUF for a model with 9B active parameters on Apple silicon.

Want an agent? K2 Horizon 7B 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 K2 Horizon 7B

Recommended for the Apple M3 Ultra (512 GB): Q8_0. 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 Q8_0 file (opens in a new tab)

huggingface.co/IFM/K2-Horizon-7B-GGUF (opens in a new tab)

ollama run hf.co/IFM/K2-Horizon-7B-GGUF:Q8_0

Original weights · Hugging Face

Full-precision files from Institute of Foundation Models, for fine-tuning, vLLM, Transformers.

huggingface.co/IFM/K2-Horizon-7B (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Institute of Foundation Models. The weights themselves download from Hugging Face.

github.com/ifm-ai/xllm (opens in a new tab)

IFM’s official training code (xLLM) for the K2 Horizon family.

git clone https://github.com/ifm-ai/xllm

Links checked 1 day ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 80Great quality (A) · 80 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.
How capable the model itself is at Q8_0, 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 M3 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.36.0 / 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.2.5 / 15
Match score78.5 / 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 M3 Ultra (512 GB)

Quant Memory needed Available Speed Runs Quality Download
Q2_K 36.1 GB 384 GB 158 tok/s Runs great 56Good quality (B) · 56 of 100: how capable the model is at Q2_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)
Q3_K_M 36.9 GB 384 GB 124 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 72/100 (quality, fit, speed and memory use) sets the ranking. GGUF files (opens in a new tab)
Q4_K_M 38.0 GB 384 GB 96.2 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 76/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q5_K_M 38.9 GB 384 GB 79.5 tok/s Runs great 77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q6_K 39.9 GB 384 GB 66.7 tok/s Runs great 79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q8_0 42.1 GB 384 GB 49.0 tok/s Runs great 80Great quality (A) · 80 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 (opens in a new tab)
F16 50.5 GB 384 GB 22.6 tok/s Runs well 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (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

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?