Instructions to use pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN 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 pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN:F16
# Run inference directly in the terminal:
llama cli -hf pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN:F16
# Run inference directly in the terminal:
llama cli -hf pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN:F16

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 pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN:F16
# Run inference directly in the terminal:
./llama-cli -hf pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN:F16

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 pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN:F16

Use Docker

docker model run hf.co/pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN:F16

LM Studio
Jan

vLLM

How to use pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN:F16

Ollama
How to use pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN with Ollama:
```
ollama run hf.co/pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN:F16
```

Unsloth Studio

How to use pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN 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 pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN 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 pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN to start chatting

How to use pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN:F16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN with Docker Model Runner:
```
docker model run hf.co/pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN:F16
```

Lemonade

How to use pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN:F16

Run and chat with the model

lemonade run user.grug-35b-v2-ROCmFP4-STRIX_LEAN-F16

List all available models

lemonade list

Hermes Agent

How to use pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN:F16

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 pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN:F16

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 "pugant/grug-35b-v2-ROCmFP4-STRIX_LEAN:F16" \
  --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"

grug-35b-v2-ROCmFP4-STRIX_LEAN / README.md

pugant

Upload README.md with huggingface_hub

30d0fcc verified 5 days ago

preview code

Raw

History Blame Contribute Delete

8.17 kB

	---
	library_name: llama.cpp
	license: apache-2.0
	base_model: ProCreations/grug-35b-v2
	tags:
	- rocmfpx
	- gfx1151
	- strix-halo
	- qwen35moe
	- moe
	- rocm
	- amdgpu
	- ROCmFP4
	pipeline_tag: image-text-to-text
	language:
	- en
	- multilingual
	version: '1.0'
	date: 2026-08-11
	quantized_by: pugant
	---

	# grug-35b-v2 — ROCmFP4-STRIX_LEAN (Strix Halo / gfx1151)

	> Version 1.0 — 2026-08-11

	## TL;DR

	`grug-35b-v2` (35B params, 3B active per token, Qwen3.5-VL-MoE family) quantized to `Q4_0_ROCMFP4_STRIX_LEAN` (type 106 preset, ~4.29 BPW). Tuned for AMD Strix Halo (gfx1151 / RDNA 3.5) with the `charlie12345/ROCmFPX` fork of llama.cpp. Runs the full vision + text multimodal model in ~17.3 GiB.

	## ⚠️ Critical warnings — read before downloading

	- Requires `charlie12345/ROCmFPX` fork of llama.cpp (built via the `kyuz0/amd-strix-halo-toolboxes` container). The type 106 (`Q4_0_ROCMFP4_STRIX_LEAN`) tensor format is INVALID in stock llama.cpp — it will refuse to load. See [Usage](#usage) below.
	- Profiled for gfx1151 only (Strix Halo / Ryzen AI Max+ 395, RDNA 3.5). Not tested on other GPUs.
	- FP4 here is software on RDNA 3.5 (no FP4 silicon units): the win is bandwidth / memory, not raw compute throughput. The Strix Halo ceiling on this MoE is bandwidth-bound, which is exactly where FP4 helps.

	## Benchmarks

	Tested on Strix Halo (AMD Ryzen AI Max+ 395, 128 GB LPDDR5X). Methodology: `llama-bench -ngl 999 -fa on -p 512 -n 128 -mmap 0`. All benchmarks for this model were run in ROCm containers (HIP backend). Since then we also benchmarked ROCmFPX quants on the Vulkan (RADV) build of the fork — see the comparison table in [Qwen3.6-35B-A3B-MTP-Q6_0_ROCMFPX](https://huggingface.co/pugant/Qwen3.6-35B-A3B-MTP-Q6_0_ROCMFPX); those numbers are on a different backend and not directly comparable.

	\| Model \| Quant \| Size \| tg128 (tok/s) \| pp512 (tok/s) \|
	\|---\|---\|---:\|---:\|---:\|
	\| grug-35b-v2 \| ROCmFP4-STRIX_LEAN \| 17.31 GiB \| 70.92 \| 1418 \|
	\| grug-35b-v2 \| Q4_K_M (baseline) \| 19.70 GiB \| 61.18 \| — \|
	\| Qwen3.6-35B-A3B (production ref) \| ROCmFP4-STRIX_LEAN \| 17.31 GiB \| 63 \| — \|

	Speed-up: +16% vs Q4_K_M (70.92 vs 61.18 tok/s tg128) at −12% size (17.31 vs 19.70 GiB). +12% vs the production Qwen3.6-35B-A3B reference.

	### System configuration at bench time

	Declared for reproducibility:

	- Bare metal host: Bosgame BeyondMax Series (`bosgame-m5`), Ubuntu 24.04.4 LTS, kernel 7.0.0-28-generic
	- CPU power profile: `balanced` (`powerprofilesctl get`) — default, NOT forced to `performance`. Representative of an out-of-the-box setup.
	- CPU scaling driver: `amd-pstate-epp`, scaling_governor `performance` (amd-pstate-epp default), EPP `performance`
	- IOMMU / iGPU power: auto (no manual tuning)

	Note: tok/s above were measured on a non-tuned system (power profile `balanced`). Users who set `powerprofilesctl set performance` may see slightly higher numbers.

	## Quantization details

	Preset `Q4_0_ROCMFP4_STRIX_LEAN` (GGUF file_type 106, ~4.29 bits/weight):

	- Attention K/V (`blk..attn_qkv.weight`, `blk..attn_v.weight`) → `q4_0_rocmfp4` (high-precision path for attention state)
	- Token embeddings (`token_embd.weight`) → `Q5_K` (preserve vocab fidelity)
	- Expert FFN (`blk..ffn__exps.weight`) → `q4_0_rocmfp4_fast` (max speed path; the bulk of MoE weights)
	- Other tensors → F32 / Q4_0_ROCMFP4_FAST as appropriate

	Reference fork: [`charlie12345/ROCmFPX`](https://github.com/charlie12345/ROCmFPX) commit `00d5452`.

	## imatrix methodology

	Generated with `llama-imatrix` (256 chunks, 16 threads, CPU-only). Calibration text from [`ProCreations/grug-think-v3-10k`](https://huggingface.co/datasets/ProCreations/grug-think-v3-10k) — public Apache-2.0 dataset, not gated: anyone can download it to replicate. Many thanks to the grug team for publishing both the model and a clean calibration set.

	- 510 entries over 733 tensors
	- Warning `partial data 99.61%` during quantization = 1/256 expert not activated in calibration (normal for MoE — see `tools/imatrix/imatrix.cpp` in llama.cpp). Negligible impact.

	## Files

	\| File \| Size \| Description \|
	\|---\|---:\|---\|
	\| `grug-35b-v2-ROCmFP4-STRIX_LEAN.gguf` \| ~17.32 GiB \| Main model (type 106) \|
	\| `mmproj-grug-35b-v2-f16.gguf` \| ~857 MB \| Vision projector (F16) \|
	\| `imatrix-grug-35b-v2.gguf` \| ~183 MB \| Importance matrix (for re-quantization) \|

	## Usage

	```bash
	# Requires the kyuz0 Strix Halo toolbox (which builds charlie12345/ROCmFPX)
	docker run --rm -p 1234:1234 --device /dev/kfd --device /dev/dri \
	-v /path/to/models:/models rocmfpx-llm-service \
	llama-server \
	-m /models/grug-35b-v2-ROCmFP4-STRIX_LEAN.gguf \
	--mmproj /models/mmproj-grug-35b-v2-f16.gguf \
	-ngl 999 -fa on --jinja -c 32768 --host 0.0.0.0 --port 1234
	```

	Notes:
	- MTP not enabled for grug. The `mtp_num_hidden_layers` field is 0 in this model (MTP was removed during fine-tuning), so it cannot be activated.
	- The `--mmproj` flag is required for the vision tower (multimodal). Without it, text-only still works.

	## How to replicate

	Textual pipeline only (no published scripts):

	1. Build the `docker-llm-service-convert` image from `kyuz0/amd-strix-halo-toolboxes` + `charlie12345/ROCmFPX` (commit `00d5452` or later main HEAD — must contain `MODEL_ARCH.QWEN35MOE`).
	2. Download the BF16 safetensors from `ProCreations/grug-35b-v2`.
	3. Convert to GGUF with `convert_hf_to_gguf.py` (inside the container).
	4. Generate the imatrix with `llama-imatrix` using `ProCreations/grug-think-v3-10k` (256 chunks).
	5. Quantize: `llama-quantize <bf16>.gguf <out>.gguf Q4_0_ROCMFP4_STRIX_LEAN 16`.

	## Attribution & model tree

	```
	Qwen3.5-VL-MoE (base architecture)
	└── ornith-ai/Ornith-1.0-35B (MIT)
	└── ProCreations/grug-35b-v2 (Apache-2.0)
	└── this GGUF (ROCmFP4-STRIX_LEAN)
	```

	- Base model: [`ProCreations/grug-35b-v2`](https://huggingface.co/ProCreations/grug-35b-v2) (Apache-2.0)
	- Quantization fork: [`charlie12345/ROCmFPX`](https://github.com/charlie12345/ROCmFPX) (MIT)
	- Container runtime: [`kyuz0/amd-strix-halo-toolboxes`](https://github.com/kyuz0/amd-strix-halo-toolboxes)

	## License

	Apache-2.0 (inherited from `ProCreations/grug-35b-v2`). Derivative work: original model and its license are preserved. See [`LICENSE`](./LICENSE) and [`NOTICE`](./NOTICE).

	## Acknowledgements

	Built on the shoulders of giants:

	- [kyuz0/amd-strix-halo-toolboxes](https://github.com/kyuz0/amd-strix-halo-toolboxes) — Strix Halo container runtime
	- [charlie12345/ROCmFPX](https://github.com/charlie12345/ROCmFPX) — llama.cpp fork with ROCmFP4 presets (type 106)
	- [ProCreations](https://huggingface.co/ProCreations) — grug-35b-v2 + the grug-think-v3-10k calibration dataset
	- [ornith-ai / DeepReinforce Team](https://huggingface.co/deepreinforce-ai) — Ornith-1.0-35B, the base of grug
	- [llama.cpp](https://github.com/ggerganov/llama.cpp) community + Kawrakow (imatrix methodology)
	- Hardware: Bosgame BeyondMax Series (Strix Halo bare metal host)

	## Limitations & community feedback

	- Speed benchmark only. No perplexity / MMLU / quality eval is included in this release. The MoE structure is preserved bit-for-bit from the BF16 source except for the quantized tensor formats above; quality is expected to track standard Q4_K_M-class with the ROCmFP4 attention/K-V choices, but this is not measured here.
	- Profiled for gfx1151 only. Not tested on other GPUs (no Navi 3 / Navi 4 / data-center MI series numbers — feel free to share yours).
	- MTP not activated (plain inference).

	We invite the community — especially fellow Strix Halo owners — to test and share quality results. Open a Discussion on this repo.

	## Citation

	```bibtex
	@misc{grug35b2026,
	title = {grug-35b-v2},
	author = {ProCreations},
	year = {2026},
	url = {https://huggingface.co/ProCreations/grug-35b-v2}
	}
	```

	## Disclaimer

	No affiliation with AMD, Qwen, ProCreations, DeepReinforce, unsloth, kyuz0, or charlie12345. Provided as-is, without warranty. Users must comply with the base model license (Apache-2.0).