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

09/02/2027: Added the PLEQ4_0 for IQ2_S and IQ3_S
09/01/2027: 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	147.17 GiB (7.14 BPW)	Q8_0 / Q5_K / Q5_K / Q6_K	4.600285 ± 0.027992	+0.2179%	0.030432 ± 0.000210
Q5_K_M (Q4_0 PLE)	126.64 GiB (6.15 BPW)	Q8_0 / Q5_K / Q5_K / Q6_K	4.616165 ± 0.028059	+0.5638%	0.030814 ± 0.000217
Q4_K_M	126.08 GiB (6.12 BPW)	Q8_0 / Q4_K / Q4_K / Q5_K	4.618153 ± 0.028121	+0.6071%	0.041479 ± 0.000274
IQ4_XS	109.09 GiB (5.30 BPW)	Q8_0 / IQ3_S / IQ3_S / IQ4_XS	4.733298 ± 0.029068	+3.1156%	0.079730 ± 0.000510
Q4_K_M (Q4_0 PLE)	105.55 GiB (5.12 BPW)	Q8_0 / Q4_K / Q4_K / Q5_K	4.633212 ± 0.028203	+0.9352%	0.043324 ± 0.000287
IQ3_S	100.01 GiB (4.85 BPW)	Q6_K / IQ2_S / IQ2_S / IQ3_S	4.870320 ± 0.030101	+6.1006%	0.162764 ± 0.000918
IQ2_S	97.66 GiB (4.74 BPW)	Q6_K / IQ2_XS / IQ2_XS / IQ3_XXS	5.037301 ± 0.031450	+9.7383%	0.205950 ± 0.001125
IQ4_XS (Q4_0 PLE)	88.56 GiB (4.30 BPW)	Q8_0 / IQ3_S / IQ3_S / IQ4_XS	4.750635 ± 0.029142	+3.4933%	0.084118 ± 0.000515
IQ3_S (Q4_0 PLE)	79.55 GiB (3.86 BPW)	Q6_K / IQ2_S / IQ2_S / IQ3_S	4.887335 ± 0.030175	+6.4713%	0.167344 ± 0.000940
IQ2_S (Q4_0 PLE)	77.21 GiB (3.75 BPW)	Q6_K / IQ2_XS / IQ2_XS / IQ3_XXS	5.076957 ± 0.031749	+10.6023%	0.213340 ± 0.001164