Instructions to use kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-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-4.2-3B-ROCmFP4-COHERENT-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-4.2-3B-ROCmFP4-COHERENT-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-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/Granite-4.2-3B-ROCmFP4-COHERENT-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-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/Granite-4.2-3B-ROCmFP4-COHERENT-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
./llama-cli -hf kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-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/Granite-4.2-3B-ROCmFP4-COHERENT-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-GGUF:Q4_0_ROCMFP

Use Docker

docker model run hf.co/kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-GGUF:Q4_0_ROCMFP

LM Studio
Jan

vLLM

How to use kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-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-4.2-3B-ROCmFP4-COHERENT-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-GGUF:Q4_0_ROCMFP

Ollama
How to use kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-GGUF with Ollama:
```
ollama run hf.co/kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-GGUF:Q4_0_ROCMFP
```

Unsloth Studio

How to use kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-GGUF to start chatting

How to use kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-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-4.2-3B-ROCmFP4-COHERENT-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/Granite-4.2-3B-ROCmFP4-COHERENT-GGUF:Q4_0_ROCMFP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-GGUF with Docker Model Runner:
```
docker model run hf.co/kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-GGUF:Q4_0_ROCMFP
```

Lemonade

How to use kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-GGUF:Q4_0_ROCMFP

Run and chat with the model

lemonade run user.Granite-4.2-3B-ROCmFP4-COHERENT-GGUF-Q4_0_ROCMFP

List all available models

lemonade list

Hermes Agent

How to use kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-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-4.2-3B-ROCmFP4-COHERENT-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/Granite-4.2-3B-ROCmFP4-COHERENT-GGUF:Q4_0_ROCMFP

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-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-4.2-3B-ROCmFP4-COHERENT-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/Granite-4.2-3B-ROCmFP4-COHERENT-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"

Granite 4.2-3B (COHERENT) — ROCmFP4 for AMD Strix Halo (gfx1151)

I built this 4-bit ROCmFP4 quantization of ibm-granite/granite-4.2-3b on my Strix Halo box for the ROCmFPX runtime. Granite 4.2 landed this week; this is my 3-tier publish set for it.

The file


ftype	`102` — `Q4_0_ROCMFP4_COHERENT`
size	2,195,351,616 bytes (2.04 GiB)
bpw	4.79
architecture	`granite`
tensors	363
context	131,072
token embedding	Q6_K
`output.weight`	Q6_K (protected)
sha256	`694bed2934af5da4cea5df83ed40616686ba0663aad242b5bf110d1a46507778`

Type histogram, read from the finished file:

Q4_0_ROCMFP4 x280, F32 x81, Q6_K x2

What this build type is — and what it protects

Q4_0_ROCMFP4_COHERENT (ftype 102) quantizes the body to ROCmFP4 — my 4-bit UE4M3-scale layout — and deliberately protects the two tensors that hurt coherence most when crushed to 4-bit: the token embedding table and the LM head both stay at Q6_K. Because this model's head is untied, a 4-bit output.weight would degrade the logits of every single token; so I quantized with --output-tensor-type q6_K and confirmed the head landed at Q6_K by exact-name read-back. Cost: ~0.1 GiB over the unprotected 4-bit. Worth it.

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-4.2-3b file list from the HF API with ?blobs=true and recorded the real shard bytes (2 safetensors shards, 7,319,517,120 bytes total — never the index total_size).
Downloaded and byte-verified all 15 files against that manifest.
Converted with convert_hf_to_gguf.py from my rocmfpx-dspark-halo tree (4eca07e), --outtype bf16 → 363 tensors, 7,323,461,696 bytes.
Quantized with the same tree's llama-quantize at 16 threads and --output-tensor-type q6_K. Dry-run estimate 2,090.24 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 (MemAvailable ~11.6 GiB before load, ~8.2 GiB after). 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)	71.55 t/s over 128 tokens
prompt processing	19 tokens in 46.3 ms

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

Please use the following reasoning steps: 1. Identify the main component of granite rock. 2. State the composition of granite rock. … (the model answered in its native function-calling/thinking scaffold — real, structured generation)

⚠️ Stock llama.cpp will not load this file

Q4_0_ROCMFP4_COHERENT is a custom tensor format that exists only in the ROCmFPX fork of llama.cpp.

llama-server -m granite-4.2-3b-Q4_0_ROCMFP4_COHERENT.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-4.2-3b (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-4.2-3B

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	1.92 GiB	60.69
`COHERENT`	my 4-bit ROCmFP4 tier with the Q6_K-protected head — the balance I run day to day	2.04 GiB	71.55
`Q8_0`	straight 8-bit ROCmFPX — highest fidelity I publish	3.52 GiB	46.36
`Q8_0-AGENT`	8-bit ROCmFPX with the agent-tuned tensor set — for tool-calling work where precision matters	3.59 GiB	50.47

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-4.2-3b

Downloads last month: 75

GGUF

Model size

4B params

Architecture

granite

Hardware compatibility

4-bit

Model tree for kingjones777/Granite-4.2-3B-ROCmFP4-COHERENT-GGUF

Base model

ibm-granite/granite-4.1-3b-base

Finetuned

ibm-granite/granite-4.2-3b

Quantized

(25)

this model