Instructions to use kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-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/GLM-4.7-Flash-ROCmFP4-STRIX-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/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-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/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-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/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
./llama-cli -hf kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-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/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF:Q4_0_ROCMFP

Use Docker

docker model run hf.co/kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF:Q4_0_ROCMFP

LM Studio
Jan

vLLM

How to use kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-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/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF:Q4_0_ROCMFP

Ollama
How to use kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF with Ollama:
```
ollama run hf.co/kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF:Q4_0_ROCMFP
```

Unsloth Studio

How to use kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-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/GLM-4.7-Flash-ROCmFP4-STRIX-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/GLM-4.7-Flash-ROCmFP4-STRIX-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/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF to start chatting

How to use kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-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/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF:Q4_0_ROCMFP

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": "kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF:Q4_0_ROCMFP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-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/GLM-4.7-Flash-ROCmFP4-STRIX-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/GLM-4.7-Flash-ROCmFP4-STRIX-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"

Docker Model Runner
How to use kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF with Docker Model Runner:
```
docker model run hf.co/kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF:Q4_0_ROCMFP
```

Lemonade

How to use kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF:Q4_0_ROCMFP

Run and chat with the model

lemonade run user.GLM-4.7-Flash-ROCmFP4-STRIX-GGUF-Q4_0_ROCMFP

List all available models

lemonade list

Hermes Agent

How to use kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-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/GLM-4.7-Flash-ROCmFP4-STRIX-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/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF:Q4_0_ROCMFP

Run Hermes

hermes

Atomic Chat

GLM-4.7-Flash ROCmFP4 STRIX (GGUF) — AMD Ryzen AI Max+ 395 / Strix Halo / gfx1151

First public ROCmFP4 quant of the full GLM-4.7-Flash weights for AMD Ryzen AI Max+ 395 (gfx1151 / Radeon 8060S).

The existing ROCm-flavoured GLM-4.7 quants on the Hub are all of the pruned REAP-23B-A3B variant. This is the full 30B model, not a pruned one.

⚠️ Not compatible with upstream llama.cpp. Requires the charlie12345/ROCmFPX fork built with HIP + ROCmFP4 kernels.

Files

File	Size	Notes
`GLM-4.7-Flash-Q4_0_ROCMFP4_STRIX.gguf`	14.93 GiB	4.28 BPW (quantize report)

Base model: zai-org/GLM-4.7-Flash BF16 source: unsloth/GLM-4.7-Flash-GGUF BF16/ 2 shards, 55.79 GiB total (16.00 BPW)

Hardware / stack (validated)

Ryzen AI Max+ 395, gfx1151, 128 GB unified
ROCm 7.2.4
Fork: charlie12345/ROCmFPX @ b41ce12

Build recipe

llama-quantize \
  GLM-4.7-Flash-BF16-00001-of-00002.gguf \
  GLM-4.7-Flash-Q4_0_ROCMFP4_STRIX.gguf \
  Q4_0_ROCMFP4_STRIX

Q4_0_ROCMFP4_STRIX (type 105) is the Strix Halo attention-K/V quality recipe. Dry-run predicted 15278.74 MiB @ 4.28 BPW and the output matched exactly.

Serving

llama-server --host 127.0.0.1 --port 8080 \
  --model GLM-4.7-Flash-Q4_0_ROCMFP4_STRIX.gguf \
  -dev ROCm0 -ngl 999 -fa on --no-mmap \
  --ctx-size 65536 --parallel 1 -b 2048 -ub 1024 -t 16 --poll 50 --jinja \
  --reasoning-format deepseek --chat-template-kwargs '{"enable_thinking":false}'

⚠️ --chat-template-kwargs '{"enable_thinking":false}' matters. With thinking on, reasoning consumes the token budget and answers get truncated at ordinary max_tokens values. Also use the chat endpoint — raw /completion with a bare instruction makes this model emit repetition loops.

Measured

Against the UD-Q4_K_XL GGUF of the same model on the same machine, chat endpoint, thinking off:

	this quant	UD-Q4_K_XL
size	14.93 GiB	16.32 GiB
quality battery	22 / 24	22 / 24
tok/s (ROCm)	56.1	48.1

The battery is 24 items: 8 code tasks graded by executing the generated function against assertions, 8 long-tail factual questions, 4 multilingual, 4 maths. Both quants scored 22/24 — parity — though they fail different items, which is sampling noise rather than quantization damage.

ngram-map-k adds roughly 1.05× on top and is worth enabling for input-grounded work (code edits, RAG, summarisation).

Note on layout variants

Q4_0_ROCMFP4_FAST (type 103, the "single-scale speed layout") and Q4_0_ROCMFP4_FAST_COHERENT (104) were both built and benchmarked against this one, same model, same flags, sizes within 0.1 GiB:

layout	base	+ ngram
STRIX (105)	55.4	57.3
FAST (103)	53.9	55.0
FAST_COHERENT (104)	53.9	56.7

FAST is ~3% slower than the quality recipe despite its name, on this architecture and hardware. STRIX is both the faster and the higher-quality choice here, which is why it is the one published. Runtime knobs (micro-batch 512/2048, 32 threads, q8_0 KV cache, --poll 0) were all neutral-to-negative — quantizing the KV cache changing nothing indicates the bottleneck is weight bandwidth rather than KV.

License

Follow the base model (zai-org/GLM-4.7-Flash) license terms.

Other public builds of this model

Compiled from Hugging Face repository metadata — file sizes, shipped files, quant variant as named by each repo. No third-party build was run or benchmarked here, so this table makes no speed or quality claim about any of them. It is here so you can see the size and format options at a glance and pick what fits your hardware.

Repository	Largest model file	Variant	Ships	Downloads	Likes
`GadflyII/GLM-4.7-Flash-NVFP4`	5.00 GiB	NVFP4	safetensors	161900	70
`GadflyII/GLM-4.7-Flash-MTP-NVFP4`	5.00 GiB	NVFP4	safetensors	514	5
`cafonez/GLM-4.7-Flash-REAP-23B-A3B-ROCmFP4-GGUF`	11.45 GiB	ROCmFP4	single model file	98	0
`kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF` (this repo)	14.93 GiB	STRIX	single model file	77	0

Base model: zai-org/GLM-4.7-Flash. Generated from Hub metadata; download counts move over time.

Acknowledgements

This build would not exist without the work below. Please star and follow these projects — the quantisation format used here is their engineering, not mine.

ROCmFPX — maintained by charlie12345 / caf The ROCmFP4 / ROCmFPX tensor formats (ggml types 100–106) exist only in this fork. Every ROCmFP4 file in this repository was produced with its llama-quantize, and runs on its runtime. The fork also credits collaborators ciru-ai, Tom Turney, PlunderStruck and Aydan S., and acknowledges AMD for hardware support. Licensed MIT, based on upstream llama.cpp.

llama.cpp — ggml-org and contributors The inference engine, GGUF format and conversion tooling everything here is built on.

AMD ROCm The compute platform these builds target — ROCm 7.2.4 on gfx1151 / Radeon 8060S.

Base model authors — see base_model in the metadata above; all model weights, licences and capabilities are theirs. This repository contributes quantisation and measurement only.

If you use these files, please credit ROCmFPX alongside this repository.

Downloads last month: 212

GGUF

Model size

30B params

Architecture

deepseek2

Hardware compatibility

4-bit

Model tree for kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF

Base model

zai-org/GLM-4.7-Flash

Quantized

(98)

this model

kingjones777
/

GLM-4.7-Flash-ROCmFP4-STRIX-GGUF

GLM-4.7-Flash ROCmFP4 STRIX (GGUF) — AMD Ryzen AI Max+ 395 / Strix Halo / gfx1151

Files

Hardware / stack (validated)

Build recipe

Serving

Measured

Note on layout variants

License

Other public builds of this model

Acknowledgements

Model tree for kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF

Space using kingjones777/GLM-4.7-Flash-ROCmFP4-STRIX-GGUF 1