Instructions to use Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_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 Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_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 Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF:Q8_0

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 Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF:Q8_0

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 Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF:Q8_0

Use Docker

docker model run hf.co/Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_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": "Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF:Q8_0

Ollama
How to use Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF with Ollama:
```
ollama run hf.co/Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF:Q8_0
```

Unsloth Studio

How to use Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-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 Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-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 Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF to start chatting

How to use Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_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 Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF:Q8_0

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": "Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_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 Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF:Q8_0

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 "Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF:Q8_0" \
  --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 Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF with Docker Model Runner:
```
docker model run hf.co/Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF:Q8_0
```

Lemonade

How to use Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF:Q8_0

Run and chat with the model

lemonade run user.Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_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 Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF:Q8_0

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 Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

Qwen3-30B-A3B selective precision, attention Q8_0 / experts Q4_0 (GGUF)

Run it

This file is 18.0 GB, so it wants a machine with roughly 20 GB of usable memory or more.

# Apple Silicon Mac
curl -L https://github.com/Joakimpalm-Zen/xyntetik-runner/releases/latest/download/runner-macos-arm64.tar.gz | tar xz
curl -L -o Qwen3-30B-A3B-expq4_0-attnq8_0.gguf \
  https://huggingface.co/Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF/resolve/main/Qwen3-30B-A3B-expq4_0-attnq8_0.gguf
./runner-macos-arm64 -m Qwen3-30B-A3B-expq4_0-attnq8_0.gguf -i

Linux and Windows builds are on the same release page. Any GGUF runtime with qwen3moe support should load it: every tensor is an ordinary GGUF type, only the per-tensor assignment is unusual.

This is not a uniform quantization. It is a precision PLAN: the expert banks (the bulk of a MoE's bytes) are Q4_0 while attention, embeddings and every shared tensor stay Q8_0. Category-wise:

Model	Expert tensors	Attention/shared	Size	Category
Qwen3-30B-A3B Q8_0 (Qwen)	Q8_0	Q8_0	32.48 GB	official, the source
Qwen3-30B-A3B Q4_K_M (Qwen)	Q4_K/Q6_K	Q4_K class	18.56 GB	official uniform quant
this file	Q4_0	Q8_0	17.99 GB	selective-precision derivative

File: Qwen3-30B-A3B-expq4_0-attnq8_0.gguf (17,988,417,024 bytes)
SHA256: df02efa815a74e6207f9e01f2d38272c1e2718bb23aec544709a02a2c7d5b206
Source: Qwen/Qwen3-30B-A3B-GGUF -> Qwen3-30B-A3B-Q8_0.gguf (SHA256 4ad960d180b16f56024f5b704697e5dd5b0837167c2e515ef0569abfc599743c, verified byte for byte against the repo's LFS record before quantizing)

Why this split: the methodology

Produced with the open tooling in Xyntetik Runner:

Plan: --type-plan applies per-tensor precision rules while rewriting; first matching rule wins. The exact plan for this file:

{"default": "keep", "rules": [{"match": "_exps.weight", "type": "q4_0"}]}

With a Q8_0 source, "keep" leaves attention, embeddings and shared tensors at Q8_0; the single rule sends every stacked expert bank to Q4_0. 2. Build: runner -m Qwen3-30B-A3B-Q8_0.gguf --quantize out.gguf --type-plan plan.json. The quantizer's integrity gate asserts every tensor outside the rules is byte-for-byte identical to the source, not merely that the file loads. 3. Gate: zero-point self-check first (exact: 0.0 KLD / 100% top-1), then 400 teacher-forced positions against the Q8_0 source (scripts/kld-compare-raw.py, greedy, KLD over the union of both sides' top-20 logprobs).

A note on granularity: per-EXPERT precision is not representable in GGUF. Experts are stored stacked, one tensor per layer, and a GGUF tensor carries exactly one type. Per tensor CLASS is the finest split the format allows, and it turns out to be the effective one.

Validation: it passes where the uniform quant fails

Publication bar (this project's, adopted 2026-08-14): margin-qualified top-1 at or above 97% AND mean KLD at or below 0.05 vs the source, over 400 positions. Plain top-1 is always reported beside it.

artifact	size	plain top-1	margin-qualified top-1	mean KLD	verdict
this file	17.99 GB	90.75%	99.50%	0.034	PASS
official uniform Q4_K_M	18.56 GB	79.00%	94.75%	0.114	FAIL

Same source, same protocol, same day, same machine. The selective plan is smaller than the uniform k-quant and 3.3x closer to the source: for a MoE model, precision should not be spent uniformly. The expert bulk tolerates four bits; attention does not.

MoE KLD on this harness carries small cache-state variability in the fourth decimal, so KLD is quoted to three decimals (raw gate JSONs, with per-position records, are in the Xyntetik suite evidence).

Scope and limits

The gate measures agreement with the source model's own distribution, not downstream capability. This artifact has not been benchmarked on tasks.
17.99 GB does not fit a 16 GB machine. Getting under that envelope needs the expert banks at three bits (Q3_K), which this quantizer does not write yet; that is recorded as the open item, not implied.
Expert COUNT is untouched: all 128 experts, top-8 routing, exactly the source's geometry. This is precision reallocation, not pruning (this model measurably does not tolerate pruning; see the account's Qwen3-Coder keep-120 card for the model that does).

Publication policy

This project publishes only artifacts that passed its quality gate, and re-measures published claims under its current standard: one earlier artifact (gpt-oss-20b keep-30) was re-gated under this bar, failed it, and its card now says so plainly. This file passes the same bar that superseded that one. An optimization does not pass because the file got smaller; it has to preserve the model and produce a configuration worth running.

Downloads last month: -

GGUF

Model size

31B params

Architecture

qwen3moe

Hardware compatibility

8-bit

Model tree for Joakimpalm-Zen/Qwen3-30B-A3B-selective-attnQ8_0-expQ4_0-GGUF

Base model

Qwen/Qwen3-30B-A3B-Base

Finetuned

Qwen/Qwen3-30B-A3B

Quantized

(135)

this model