LLMs · Institute of Foundation Models

K2-Horizon (375B-A23B)

Name: K2-Horizon (375B-A23B)
Author: Institute of Foundation Models

Parameters: 379B (23.0B active)
Architecture: Mixture of experts
Max context: 512K tokens
License: apache-2.0
Released: 2026-09

How to run it

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/bartowski/K2-Horizon-375B-A23B-GGUF (opens in a new tab)

ollama run hf.co/bartowski/K2-Horizon-375B-A23B-GGUF

Original weights · Hugging Face

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

huggingface.co/IFM/K2-Horizon-375B-A23B (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 open 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.

Apps that run K2-Horizon (375B-A23B)

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

LM Studio

Point-and-click: search, download and chat in one window.

Also good:

Windows PC, NVIDIA GPU

LM Studio

Point-and-click: search, download and chat in one window.

Also good:

Windows PC, AMD Radeon

Lemonade

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

Also good:

Linux, NVIDIA GPU

LM Studio

Point-and-click: search, download and chat in one window.

Also good:

Linux server, 80 GB+ GPUs

vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

Also good:

App	Type	Opens it as	Systems	Engine	Start
LM Studio	Desktop app	GGUF	macOSWindowsLinux	llama.cpp, MLX	Open in LM Studio
Ollama	CLI + API	GGUF from Hugging Face	macOSWindowsLinux	llama.cpp, MLX	`ollama run hf.co/bartowski/K2-Horizon-375B-A23B-GGUF:Q4_K_M`
llama.cpp	CLI + API	GGUF	macOSWindowsLinux	llama.cpp	`llama-server -hf bartowski/K2-Horizon-375B-A23B-GGUF:Q4_K_M`
Jan	Desktop app	GGUF	macOSWindowsLinux	llama.cpp, MLX	Open in Jan
vLLM	Server	Original weights	WSLWindowsLinux	vLLM	`vllm serve IFM/K2-Horizon-375B-A23B`
SGLang	Server	Original weights	WSLWindowsLinux	SGLang	`python3 -m sglang.launch_server --model-path IFM/K2-Horizon-375B-A23B`
Docker Model Runner	CLI + API	GGUF	macOSWindowsLinux	llama.cpp, vLLM	`docker model run hf.co/bartowski/K2-Horizon-375B-A23B-GGUF:Q4_K_M`
Lemonade	Desktop app	GGUF	macOSWindowsLinux	llama.cpp, ONNX Runtime GenAI	`lemonade pull bartowski/K2-Horizon-375B-A23B-GGUF:Q4_K_M`
Unsloth Desktop	Desktop app	GGUF	macOSWindowsLinux	llama.cpp, MLX, stable-diffusion.cpp	Open in Unsloth Desktop
Atomic Chat	Desktop app	GGUF	macOSWindowsLinux	llama.cpp, MLX-VLM	Open in Atomic Chat
Pi	Coding agent	GGUF	macOSWindowsLinux	uses llama.cpp or MLX LM	Point it at a llama.cpp or MLX LM server
Hermes Agent	Assistant	GGUF	macOSWSLWindowsLinux	uses llama.cpp or MLX LM	Point it at a llama.cpp or MLX LM server
OpenClaw	Assistant	GGUF	macOSWSLWindowsLinux	uses llama.cpp or MLX LM	Point it at a llama.cpp or MLX LM server
OpenCode	Coding agent	GGUF	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Codex CLI	Coding agent	GGUF	macOSWSLWindowsLinux	uses Ollama or any OpenAI-compatible server	Point it at a llama.cpp or MLX LM server
OpenHands	Coding agent	GGUF	macOSWSLWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Zed	Coding agent	GGUF	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Cline	Coding agent	GGUF	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Open Interpreter	Coding agent	GGUF	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Goose	Coding agent	GGUF	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Aider	Coding agent	GGUF	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Crush	Coding agent	GGUF	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Qwen Code	Coding agent	GGUF	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Kilo Code	Coding agent	GGUF	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Open WebUI	Assistant	GGUF	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Khoj	Assistant	GGUF	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Letta	Assistant	GGUF	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
KoboldCpp	Desktop app	GGUF	macOSWindowsLinux	llama.cpp	Get KoboldCpp
Text Generation WebUI	Desktop app	GGUF	macOSWindowsLinux	llama.cpp, Transformers, ExLlamaV3	Get Text Generation WebUI
llamafile	CLI + API	GGUF	macOSWindowsLinux	llama.cpp	Get llamafile
Msty Studio	Desktop app	GGUF	macOSWindowsLinux	Ollama, llama.cpp, MLX	Open in Msty Studio
Llama (macOS)	Desktop app	GGUF	macOS	llama.cpp	Open in Llama (macOS)
RecurseChat	Desktop app	GGUF	macOS	llama.cpp	Open in RecurseChat
node-llama-cpp	Library	GGUF	macOSWindowsLinux	llama.cpp	Get node-llama-cpp
Continue	Coding agent	GGUF	macOSWindowsLinux	uses Ollama, LM Studio or llama.cpp	Point it at a llama.cpp or MLX LM server
SillyTavern	Assistant	GGUF	macOSWindowsLinux	uses Ollama, LM Studio or llama.cpp	Point it at a llama.cpp or MLX LM server
LibreChat	Assistant	GGUF	macOSWindowsLinux	uses Ollama, LM Studio or llama.cpp	Point it at a llama.cpp or MLX LM server
Cherry Studio	Assistant	GGUF	macOSWindowsLinux	uses Ollama, LM Studio or llama.cpp	Point it at a llama.cpp or MLX LM server
Chatbox	Assistant	GGUF	macOSWindowsLinux	uses Ollama, LM Studio or llama.cpp	Point it at a llama.cpp or MLX LM server
PrivateGPT	Assistant	GGUF	macOSWindowsLinux	uses Ollama, LM Studio or llama.cpp	Point it at a llama.cpp or MLX LM server
PocketPal AI	Mobile app	GGUF	iOSAndroid	llama.cpp	App Store Google Play
ChatterUI	Mobile app	GGUF	Android	llama.cpp	Download the APK
LLM Farm	Mobile app	GGUF	iOS	llama.cpp	Not on the App Store or TestFlight for now (checked 2026-11-09).

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps. Try another context length.

Quantization	Quality	Weights	Total at 8K context	Total at 32K context	Download
`Q2_K`	Low	152 GB	154 GB	160 GB	GGUF · folder (opens in a new tab)
`Q3_K_M`	Low	186 GB	188 GB	195 GB	GGUF · folder (opens in a new tab)
`Q4_K_M`	Good	231 GB	234 GB	240 GB	GGUF · folder (opens in a new tab)
`Q5_K_M`	High	269 GB	272 GB	278 GB	GGUF · folder (opens in a new tab)
`Q6_K`	High	311 GB	314 GB	320 GB	GGUF · folder (opens in a new tab)
`Q8_0`	Very high	402 GB	405 GB	411 GB	GGUF · folder (opens in a new tab)
`F16`	Full	758 GB	761 GB	767 GB	Original weights (opens in a new tab)

Best hardware for K2-Horizon (375B-A23B)

Quality	Hardware	Quant	Memory	Speed	Runs
89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.	Apple M3 Ultra (512 GB)	`Q4_K_M`	265 GB / 384 GB	33.4 tok/s	Runs great
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	Apple M3 Ultra (256 GB)	`Q2_K`	170 GB / 192 GB	51.8 tok/s	Runs welltight fit
91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.	Apple M5 Ultra (512 GB)	`Q5_K_M`	303 GB / 384 GB	39.3 tok/s	Runs great
91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.	AMD Instinct MI350X	`Q5_K_M`	286 GB / 288 GB	147 tok/s	Runs welltight fit
89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.	AMD Instinct MI325X	`Q4_K_M`	247 GB / 256 GB	143 tok/s	Runs welltight fit
89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip	`Q4_K_M`	247 GB / 252 GB	167 tok/s	Runs welltight fit
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	AMD Instinct MI300X	`Q2_K`	164 GB / 192 GB	178 tok/s	Runs welltight fit
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	Apple M5 Ultra (256 GB)	`Q2_K`	170 GB / 192 GB	70.6 tok/s	Runs welltight fit
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA B200	`Q2_K`	163 GB / 180 GB	220 tok/s	Runs welltight fit
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA H200 141GB SXM	`Q2_K`	161 GB / 141 GB	35.5 tok/s	Runs welloffloads to RAM

Check it on your own hardware

Run it on a cluster

Devices that can’t run K2-Horizon (375B-A23B) alone can run it together. These example clusters do:

Try it with your own devices

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.