Instructions to use kingjones777/Granite-4.2-8B-ROCmFPX-Q8_0-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/Granite-4.2-8B-ROCmFPX-Q8_0-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/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF:Q8_0_ROCMFPX
# Run inference directly in the terminal:
llama cli -hf kingjones777/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF:Q8_0_ROCMFPX

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kingjones777/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF:Q8_0_ROCMFPX
# Run inference directly in the terminal:
llama cli -hf kingjones777/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF:Q8_0_ROCMFPX

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/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF:Q8_0_ROCMFPX
# Run inference directly in the terminal:
./llama-cli -hf kingjones777/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF:Q8_0_ROCMFPX

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/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF:Q8_0_ROCMFPX
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kingjones777/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF:Q8_0_ROCMFPX

Use Docker

docker model run hf.co/kingjones777/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF:Q8_0_ROCMFPX

LM Studio
Jan

vLLM

How to use kingjones777/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kingjones777/Granite-4.2-8B-ROCmFPX-Q8_0-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/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kingjones777/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF:Q8_0_ROCMFPX

Ollama

How to use kingjones777/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF with Ollama:

ollama run hf.co/kingjones777/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF:Q8_0_ROCMFPX

Unsloth Desktop

How to use kingjones777/Granite-4.2-8B-ROCmFPX-Q8_0-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/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF:Q8_0_ROCMFPX

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/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF:Q8_0_ROCMFPX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use kingjones777/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF with Docker Model Runner:
```
docker model run hf.co/kingjones777/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF:Q8_0_ROCMFPX
```

Lemonade

How to use kingjones777/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kingjones777/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF:Q8_0_ROCMFPX

Run and chat with the model

lemonade run user.Granite-4.2-8B-ROCmFPX-Q8_0-GGUF-Q8_0_ROCMFPX

List all available models

lemonade list

Hermes Agent

How to use kingjones777/Granite-4.2-8B-ROCmFPX-Q8_0-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/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF:Q8_0_ROCMFPX

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/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF:Q8_0_ROCMFPX

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use kingjones777/Granite-4.2-8B-ROCmFPX-Q8_0-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/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF:Q8_0_ROCMFPX

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/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF:Q8_0_ROCMFPX" \
  --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"

Granite 4.2-8B — ROCmFPX 8-bit reference layout for AMD Strix Halo (gfx1151)

I built this reference 8-bit ROCmFPX quantization of ibm-granite/granite-4.2-8b on my Strix Halo box.

The file


ftype	`111` — `Q8_0_ROCMFPX`
size	9,070,886,976 bytes (8.45 GiB)
bpw	8.25
architecture	`granite`
tensors	363
context	131,072
token embedding	Q8_0_ROCMFPX
`output.weight`	Q8_0_ROCMFPX
sha256	`f7b2aabad5e784b30910204c477f908623c50d8eb8a5c864ac2f79cd644127cd`

Type histogram, read from the finished file:

Q8_0_ROCMFPX x282, F32 x81

What this build type is — and what it protects

Q8_0_ROCMFPX (ftype 111) is my reference 8-bit ROCmFPx layout: every weight tensor — including token_embd.weight and output.weight — goes into the ROCmFPX 8-bit UE4M3-scale reference format. Nothing is held back at plain Q8_0 (contrast with my _AGENT tier, which keeps the output-side tensors at plain Q8_0 for tool-call coherence). At 8 bits the quality gap between the two tiers is small; take this one for size/speed, take _AGENT if you serve tools.

tie_word_embeddings is false on Granite 4.2, so output.weight is a real standalone tensor. I verified the head types by reading the finished file back by exact tensor name (token_embd.weight and output.weight — exact match, not substring).

How I built it

Manifest gate: pulled ibm-granite/granite-4.2-8b file list from the HF API with ?blobs=true and recorded the real shard bytes (4 safetensors shards, 17,583,228,032 bytes total — never the index total_size).
Downloaded and byte-verified all 17 files against that manifest.
Converted with convert_hf_to_gguf.py from my rocmfpx-dspark-halo tree (4eca07e), --outtype bf16 → 363 tensors, 17,587,421,248 bytes.
Quantized with the same tree's llama-quantize at 16 threads. Dry-run estimate 8,647.27 MiB; the real file landed within a few MiB of it.

Measured on my box

amd-halo: AMD Ryzen AI Max+ 395 (Strix Halo, gfx1151), ROCm 7.13.0, 125 GiB unified memory. Functional check, not an idle-box benchmark: 8 other llama-server seats were live on this machine while I tested. Server flags: -dev ROCm0 -fa on -ngl 999 --no-mmap -fit off -np 1 -b 2048 -c 8192 -t 16 --jinja, port 8497, greedy:


generation (server-reported)	21.49 t/s over 128 tokens
MemAvailable	12.1 GiB before load → 4.7 GiB after

Sample output (greedy, prompt "Explain in one clear sentence what granite rock is primarily made of."):

Answer: Granite is primarily made of quartz, feldspar, and mica. (continued with its own follow-up Q/A scaffolding — real structured generation)

⚠️ Stock llama.cpp will not load this file

Q8_0_ROCMFPX is a custom tensor format that exists only in the ROCmFPX fork of llama.cpp.

llama-server -m granite-4.2-8b-Q8_0_ROCMFPX.gguf -dev ROCm0 -fa on -ngl 999 -c 8192

Not measured

No benchmark sweeps, no context sweeps, no perplexity — per my build discipline this is the 3-tier publish set and one functional check per tier.

Provenance & license

Converted and quantized from ibm-granite/granite-4.2-8b (Apache 2.0). This quantized build is released under the same Apache 2.0 license. The ROCmFPX runtime is a third-party fork; its own terms apply to the runtime, not to these weights.

All my quants of Granite-4.2-8B

build	what it is	size	tok/s (full GPU offload)
`STRIX_LEAN`	my leaner 4-bit tier, Q6_K head — smallest of my 4-bit builds, the one most people want	4.53 GiB	38.33
`COHERENT`	my 4-bit ROCmFP4 tier with the Q6_K-protected head — the balance I run day to day	4.81 GiB	39.35
`Q8_0`	straight 8-bit ROCmFPX — highest fidelity I publish	8.45 GiB	21.49
`Q8_0-AGENT`	8-bit ROCmFPX with the agent-tuned tensor set — for tool-calling work where precision matters	8.60 GiB	23.38

All measured by me on a Ryzen AI MAX+ 395 (Strix Halo, gfx1151, ROCm 7.2.4) with the whole model on GPU (-ngl 999), 128-token greedy generation. A dash means I haven't measured that one yet — I won't put a number in a card I didn't measure.

Base model: ibm-granite/granite-4.2-8b

Downloads last month: 113

GGUF

Model size

9B params

Architecture

granite

Hardware compatibility

8-bit

Model tree for kingjones777/Granite-4.2-8B-ROCmFPX-Q8_0-GGUF

Base model

ibm-granite/granite-4.1-8b-base

Finetuned

ibm-granite/granite-4.2-8b

Quantized

(37)

this model