Instructions to use sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-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 sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-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 sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF:NVFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF:NVFP4

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 sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
./llama-cli -hf sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF:NVFP4

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 sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF:NVFP4

Use Docker

docker model run hf.co/sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF:NVFP4

LM Studio
Jan
Ollama
How to use sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF with Ollama:
```
ollama run hf.co/sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF:NVFP4
```

Unsloth Studio

How to use sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-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 sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-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 sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF to start chatting

How to use sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF:NVFP4

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": "sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF:NVFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF:NVFP4

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 "sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF:NVFP4" \
  --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 sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF:NVFP4
```

Lemonade

How to use sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF:NVFP4

Run and chat with the model

lemonade run user.Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF-NVFP4

List all available models

lemonade list

Hermes Agent

How to use sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-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 sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF:NVFP4

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 sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF:NVFP4

Run Hermes

hermes

Atomic Chat

Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF

This repository contains a GGUF conversion of Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4, which is an NVFP4 compressed-tensors quantized version of RangerX/Qwen3.6-35B-REAP-Pruned-ratio-0.5.

Conversion

The GGUF file was produced from the local Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4 Hugging Face checkpoint with a patched llama.cpp converter that handles compressed-tensors NVFP4 tensors for this model.

uv run /home/sroecker/src/llama.cpp/convert_hf_to_gguf.py \
  --verbose \
  --outtype auto \
  --outfile Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4.gguf \
  Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4

The converter detected BF16 tensors and exported the model with GGUF file type 39. The resulting GGUF contains 1293 tensors:

280 NVFP4 tensors
152 BF16 tensors
861 F32 tensors

llama.cpp Patch Notes

The conversion was based on the process documented in knoopx/Qwen3.6-35B-A3B-NVFP4-GGUF. The converter-side changes used here follow the approach from the open llama.cpp PR #21095, which adds conversion support for Hugging Face NVFP4 models quantized with compressed-tensors. Native Blackwell NVFP4 CUDA runtime support is tracked separately in #22196.

The local converter used here includes the relevant converter-side handling:

treat compressed-tensors checkpoints with format nvfp4-pack-quantized as NVFP4 inputs
pass packed NVFP4 tensors through the NVFP4 GGUF repacker instead of dequantizing them
map compressed-tensors names such as weight_packed, weight_global_scale, and input_global_scale to the ModelOpt-style names expected by the repacker
convert global scale tensors to reciprocal scale values for the GGUF NVFP4 layout
register the Qwen3.6 BPE pre-tokenizer hash 1444df51289cfa8063b96f0e62b1125440111bc79a52003ea14b6eac7016fd5f as qwen35

Files

File	Size
`Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4.gguf`	`13G`

Downloads last month: 2,584

GGUF

Model size

19B params

Architecture

qwen35moe

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Finetuned

RangerX/Qwen3.6-35B-REAP-Pruned-ratio-0.5

Quantized

(4)

this model

Collection including sroecker/Qwen3.6-35B-REAP-Pruned-ratio-0.5-NVFP4-GGUF

Compressed Models

Collection

3 items • Updated May 5