Instructions to use kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF:Q4_0_ROCMFP

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF:Q4_0_ROCMFP

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
./llama-cli -hf kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF:Q4_0_ROCMFP

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF:Q4_0_ROCMFP

Use Docker

docker model run hf.co/kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF:Q4_0_ROCMFP

LM Studio
Jan

vLLM

How to use kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF:Q4_0_ROCMFP

Ollama
How to use kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF with Ollama:
```
ollama run hf.co/kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF:Q4_0_ROCMFP
```
Unsloth Desktop

How to use kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF:Q4_0_ROCMFP

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF:Q4_0_ROCMFP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF:Q4_0_ROCMFP
```

Lemonade

How to use kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF:Q4_0_ROCMFP

Run and chat with the model

lemonade run user.K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF-Q4_0_ROCMFP

List all available models

lemonade list

Hermes Agent

How to use kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF:Q4_0_ROCMFP

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF:Q4_0_ROCMFP

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF:Q4_0_ROCMFP

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF:Q4_0_ROCMFP" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF / README.md

kingjones777

K2-Horizon-MoVA-36B-A4B ROCmFP4: dual-expert MoE, 4 tiers measured on gfx1151

7e5701f verified 4 days ago

preview code

Raw

History Blame Contribute Delete

5.68 kB

	---
	license: apache-2.0
	base_model:
	- IFM/K2-Horizon-MoVA-36B-A4B
	base_model_relation: quantized
	tags:
	- gguf
	- rocm
	- vulkan
	- rocmfp4
	- strix-halo
	- gfx1151
	- amd
	- moe
	- reasoning
	- k2-horizon
	pipeline_tag: text-generation
	---

	# K2-Horizon-MoVA-36B-A4B — ROCmFP4 for AMD Strix Halo (gfx1151)

	Four ROCmFP4/ROCmFPX tiers of [`IFM/K2-Horizon-MoVA-36B-A4B`](https://huggingface.co/IFM/K2-Horizon-MoVA-36B-A4B),
	quantised from the official BF16 GGUF and measured on a Ryzen AI Max+ 395 (Radeon 8060S, gfx1151,
	128 GB unified, ROCm 7.2.4). This is the dual-expert `k2_horizon` MoVA architecture — 36B total
	parameters, ~4B active — with two independent expert systems: a 64-way MoVA value-expert bank
	(top-4) alongside a 100-way MoE feed-forward (top-8), 48 layers, hidden 2560, and it is a
	reasoning model.

	Every number on this card was measured on these exact files. Nothing is estimated. As an
	A4B MoE, it decodes far faster than a dense 32B on the same hardware.

	## Which file should I use?

	\| file \| ftype \| size \| decode (HIP) \| prefill (HIP) \| use it for \|
	\|---\|---\|---\|---\|---\|---\|
	\| `K2-Horizon-MoVA-36B-A4B-Q4_0_ROCMFP4_FAST.gguf` \| 103 \| 18.57 GiB \| 41.0 t/s \| 1238 t/s \| default — fastest on both axes \|
	\| `K2-Horizon-MoVA-36B-A4B-Q4_0_ROCMFP4_STRIX_LEAN.gguf` \| 106 \| 18.67 GiB \| 41.0 t/s \| 1227 t/s \| same speed, Q5_K embeddings \|
	\| `K2-Horizon-MoVA-36B-A4B-Q4_0_ROCMFP4_COHERENT.gguf` \| 102 \| 19.81 GiB \| 39.5 t/s \| 1114 t/s \| most bits in the 4-bit family \|
	\| `K2-Horizon-MoVA-36B-A4B-Q8_0_ROCMFPX_AGENT.gguf` \| 115 \| 36.45 GiB \| 28.9 t/s \| 1183 t/s \| 8-bit, agent/tool-call routing \|

	Start with `FAST` — fastest on both axes here, all four answer correctly. Take `AGENT` only if
	you specifically want 8-bit weights.

	## Quick start — the backend is one flag

	```bash
	# HIP / ROCm — best prefill (long prompts, RAG, agentic)
	llama-server -m K2-Horizon-MoVA-36B-A4B-Q4_0_ROCMFP4_FAST.gguf \
	-dev ROCm0 -fa on -ngl 999 --no-mmap -fit off -np 1 \
	-b 2048 -ub 1024 -t 16 --poll 100 -c 8192 --jinja

	# Vulkan — SAME FILE. Only -dev changes.
	llama-server -m K2-Horizon-MoVA-36B-A4B-Q4_0_ROCMFP4_FAST.gguf -dev Vulkan0 ...
	```

	### ⛔ You need a build with BOTH `k2_horizon` and the ROCmFP4 types

	These declare `general.architecture = k2-horizon` and use the ROCmFP4/ROCmFPX tensor types
	(ggml 100-119). No single public build has both yet:

	- `k2_horizon` arch (incl. the MoVA dual-expert graph) — [MBZUAI-IFM llama.cpp fork](https://github.com/MBZUAI-IFM/llama.cpp/tree/model/K2Horizon); upstream PR in progress.
	- ROCmFP4/ROCmFPX types — [`ROCmFPX`](https://github.com/ROCmFPX/ROCmFPX).

	This repo ships `k2-horizon-on-rocmfpx.patch` — the arch applied onto a ROCmFPX base, the exact
	tree these files were built and verified against:

	```bash
	git clone https://github.com/ROCmFPX/ROCmFPX.git && cd ROCmFPX
	curl -fLO https://huggingface.co/kingjones777/K2-Horizon-MoVA-36B-A4B-ROCmFP4-GGUF/resolve/main/k2-horizon-on-rocmfpx.patch
	git apply k2-horizon-on-rocmfpx.patch
	cmake -B build -DGGML_HIP=ON -DGGML_VULKAN=ON -DAMDGPU_TARGETS=gfx1151 -DGGML_NATIVE=ON -DCMAKE_BUILD_TYPE=Release
	cmake --build build -j$(nproc)
	```

	## ⛔ Serving note — this is a reasoner

	MoVA-36B emits chain-of-thought into `reasoning_content` before answering. A short budget returns
	HTTP 200 with empty `content` and the tokens in `reasoning` — the model thinking, not a broken
	file. Give it room: ~500 tokens for short answers and tool calls, more for long-form. Verified: at
	40 tokens `content` was empty; at 500 it answered correctly.

	## Head handling

	Quantised at each tier's native routing with no forced `--output-tensor-type` override; the tiers
	are posted as-built.

	## Reproduction block

	```
	model : IFM/K2-Horizon-MoVA-36B-A4B (official BF16 GGUF, K2-Horizon-36B-BF16.gguf, 74.9 GB)
	arch k2-horizon MoVA (dual-expert MoE): 36B total / ~4B active,
	mova_num_experts 64 top-4 + num_experts 100 top-8, 48 layers, hidden 2560
	port : MBZUAI-IFM/llama.cpp @ model/K2Horizon (35999d1) k2_horizon arch
	applied onto ROCmFPX fork @ 85d8f7e (patch shipped in this repo)
	quantize : llama-quantize <in> <out> <ftype> (no head-type override)
	Q4_0_ROCMFP4_COHERENT (102) · Q4_0_ROCMFP4_FAST (103)
	Q4_0_ROCMFP4_STRIX_LEAN (106) · Q8_0_ROCMFPX_AGENT (115)
	serve : llama-server -dev {ROCm0\|Vulkan0} -fa on -ngl 999 --no-mmap -fit off
	-np 1 -b 2048 -ub 1024 -t 16 --poll 100 -c 8192 --jinja
	box : Ryzen AI Max+ 395 / Radeon 8060S (gfx1151) / 128 GB unified, ROCm 7.2.4
	verified : dual-expert graph loads on GPU, generates correct output
	("capital of France" -> "Paris"; "capital of Japan" -> "Tokyo")
	measured : 2026-09-04
	```

	## SHA256

	```
	0f11adaada7b8b9f7aa785561f412d2de85a555fc1e2ffeddf71f972b8d576e4 K2-Horizon-MoVA-36B-A4B-Q4_0_ROCMFP4_COHERENT.gguf
	5618a8e20c3300dcb38ec7217c612edcd8fb091b23aa9e024ca7063b235e80bf K2-Horizon-MoVA-36B-A4B-Q4_0_ROCMFP4_FAST.gguf
	7fea90c3aa739652d764416741e85f563ca355ab29c8a8eb89e753a37df8e79f K2-Horizon-MoVA-36B-A4B-Q4_0_ROCMFP4_STRIX_LEAN.gguf
	e653f3855ed2c0c347e14e22593d49ced9118bf2115a7717ed2e34e5e6ff722c K2-Horizon-MoVA-36B-A4B-Q8_0_ROCMFPX_AGENT.gguf
	```

	## Credits

	[IFM / MBZUAI](https://huggingface.co/IFM) — the K2-Horizon-MoVA-36B-A4B base model
	(Apache-2.0) and the `k2_horizon` llama.cpp architecture. ROCmFP4/ROCmFPX quantisation types are the
	work of [ROCmFPX](https://github.com/ROCmFPX/ROCmFPX). This repository adds only the ROCmFP4
	quant ladder, the arch-on-ROCmFPX patch, and the measurements.