Instructions to use AesSedai/Qwen3.8-Flash-Next-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 AesSedai/Qwen3.8-Flash-Next-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 AesSedai/Qwen3.8-Flash-Next-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AesSedai/Qwen3.8-Flash-Next-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AesSedai/Qwen3.8-Flash-Next-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AesSedai/Qwen3.8-Flash-Next-GGUF:Q4_K_M

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 AesSedai/Qwen3.8-Flash-Next-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AesSedai/Qwen3.8-Flash-Next-GGUF:Q4_K_M

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 AesSedai/Qwen3.8-Flash-Next-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AesSedai/Qwen3.8-Flash-Next-GGUF:Q4_K_M

Use Docker

docker model run hf.co/AesSedai/Qwen3.8-Flash-Next-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use AesSedai/Qwen3.8-Flash-Next-GGUF with Ollama:
```
ollama run hf.co/AesSedai/Qwen3.8-Flash-Next-GGUF:Q4_K_M
```
Unsloth Desktop

How to use AesSedai/Qwen3.8-Flash-Next-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AesSedai/Qwen3.8-Flash-Next-GGUF:Q4_K_M

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": "AesSedai/Qwen3.8-Flash-Next-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use AesSedai/Qwen3.8-Flash-Next-GGUF with Docker Model Runner:
```
docker model run hf.co/AesSedai/Qwen3.8-Flash-Next-GGUF:Q4_K_M
```

Lemonade

How to use AesSedai/Qwen3.8-Flash-Next-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AesSedai/Qwen3.8-Flash-Next-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.8-Flash-Next-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use AesSedai/Qwen3.8-Flash-Next-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 AesSedai/Qwen3.8-Flash-Next-GGUF:Q4_K_M

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 AesSedai/Qwen3.8-Flash-Next-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AesSedai/Qwen3.8-Flash-Next-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AesSedai/Qwen3.8-Flash-Next-GGUF:Q4_K_M

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 "AesSedai/Qwen3.8-Flash-Next-GGUF:Q4_K_M" \
  --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"

Updates / Notes

10/03/2026: I've re-quanted all of the models to include MTP, please re-download.
09/02/2026: Added the PLEQ4_0 for IQ2_S and IQ3_S
09/01/2026: The original quants all have Q8_0 for the engram embedding tensors, and I've uploaded three variants with Q4_0 for the embedded tensors. The only difference is the Q8_0 vs Q4_0 for those tensors. I'm leaving the original quants up for those who want to use the Q8_0 PLE's.

This repo contains specialized MoE-quants for Qwen/Qwen3.8-Flash-Next. The idea being that given the huge size of the FFN tensors compared to the rest of the tensors in the model, it should be possible to achieve a better quality while keeping the overall size of the entire model smaller compared to a similar naive quantization. To that end, the quantization type default is kept in high quality and the FFN UP + FFN GATE tensors are quanted down along with the FFN DOWN tensors.

Quant	Size	Mixture	PPL	1-(Mean PPL(Q)/PPL(base))	KLD
Q5_K_M	153.07 GiB (7.32 BPW)	Q8_0 / Q5_K / Q5_K / Q6_K	4.596526 ± 0.027937	+0.1270%	0.020218 ± 0.000145
Q4_K_M	131.98 GiB (6.31 BPW)	Q8_0 / Q4_K / Q4_K / Q5_K	4.613527 ± 0.028075	+0.4973%	0.034206 ± 0.000237
IQ4_XS	114.99 GiB (5.50 BPW)	Q8_0 / IQ3_S / IQ3_S / IQ4_XS	4.739310 ± 0.029099	+3.2373%	0.076158 ± 0.000486
IQ3_S	105.98 GiB (5.07 BPW)	Q6_K / IQ2_S / IQ2_S / IQ3_S	4.863539 ± 0.030050	+5.9434%	0.160378 ± 0.000915
IQ2_S	103.63 GiB (4.96 BPW)	Q6_K / IQ2_XS / IQ2_XS / IQ3_XXS	5.043883 ± 0.031497	+9.8718%	0.205353 ± 0.001121

Quant	Size	Mixture	PPL	1-(Mean PPL(Q)/PPL(base))	KLD
Q5_K_M (Q4_0 PLE)	129.23 GiB (6.18 BPW)	Q8_0 / Q5_K / Q5_K / Q6_K	4.620130 ± 0.028097	+0.6412%	0.030943 ± 0.000212
Q4_K_M (Q4_0 PLE)	108.14 GiB (5.17 BPW)	Q8_0 / Q4_K / Q4_K / Q5_K	4.629426 ± 0.028160	+0.8437%	0.043475 ± 0.000297
IQ4_XS (Q4_0 PLE)	91.14 GiB (4.36 BPW)	Q8_0 / IQ3_S / IQ3_S / IQ4_XS	4.759109 ± 0.029230	+3.6686%	0.084406 ± 0.000531
IQ3_S (Q4_0 PLE)	82.13 GiB (3.93 BPW)	Q6_K / IQ2_S / IQ2_S / IQ3_S	4.889509 ± 0.030205	+6.5091%	0.167198 ± 0.000940
IQ2_S (Q4_0 PLE)	79.79 GiB (3.82 BPW)	Q6_K / IQ2_XS / IQ2_XS / IQ3_XXS	5.062449 ± 0.031623	+10.2763%	0.211550 ± 0.001142