Instructions to use paperniuk/Qwen3.8-Flash-Next-MTP-block with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use paperniuk/Qwen3.8-Flash-Next-MTP-block 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 paperniuk/Qwen3.8-Flash-Next-MTP-block
# Run inference directly in the terminal:
llama cli -hf paperniuk/Qwen3.8-Flash-Next-MTP-block

Install from WinGet (Windows)

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

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 paperniuk/Qwen3.8-Flash-Next-MTP-block
# Run inference directly in the terminal:
./llama-cli -hf paperniuk/Qwen3.8-Flash-Next-MTP-block

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 paperniuk/Qwen3.8-Flash-Next-MTP-block
# Run inference directly in the terminal:
./build/bin/llama-cli -hf paperniuk/Qwen3.8-Flash-Next-MTP-block

Use Docker

docker model run hf.co/paperniuk/Qwen3.8-Flash-Next-MTP-block

LM Studio
Jan
Ollama
How to use paperniuk/Qwen3.8-Flash-Next-MTP-block with Ollama:
```
ollama run hf.co/paperniuk/Qwen3.8-Flash-Next-MTP-block
```
Unsloth Desktop

How to use paperniuk/Qwen3.8-Flash-Next-MTP-block with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf paperniuk/Qwen3.8-Flash-Next-MTP-block

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": "paperniuk/Qwen3.8-Flash-Next-MTP-block"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use paperniuk/Qwen3.8-Flash-Next-MTP-block with Docker Model Runner:
```
docker model run hf.co/paperniuk/Qwen3.8-Flash-Next-MTP-block
```

Lemonade

How to use paperniuk/Qwen3.8-Flash-Next-MTP-block with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull paperniuk/Qwen3.8-Flash-Next-MTP-block

Run and chat with the model

lemonade run user.Qwen3.8-Flash-Next-MTP-block-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use paperniuk/Qwen3.8-Flash-Next-MTP-block with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf paperniuk/Qwen3.8-Flash-Next-MTP-block

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 paperniuk/Qwen3.8-Flash-Next-MTP-block

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use paperniuk/Qwen3.8-Flash-Next-MTP-block with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf paperniuk/Qwen3.8-Flash-Next-MTP-block

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 "paperniuk/Qwen3.8-Flash-Next-MTP-block" \
  --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"

Qwen3.8-Flash-Next MTP block (1.4 GB)

The MTP (multi token prediction) block of Qwen3.8-Flash-Next as a standalone GGUF: the 32 blk.48.* tensors and the model metadata, nothing else. It is meant for GGUF releases that ship without the block, such as ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF, so that speculative decoding works without downloading a second full model.

File	Size	SHA-256
`Qwen3.8-Flash-Next-MTP-block.gguf`	1.52 GB (1.41 GiB)	`bbb435d7ba548ddd5b2d6f660863bf56836e76f2b7d7ef98fa2c983fd0fefae1`

Quantization: Q4_K gate/up experts, MXFP4 down experts, Q8_0 dense projections, F16 hyper-connection mixers.

Where it comes from

The tensors are copied byte for byte from ivanfioravanti/Qwen3.8-Flash-Next-DS4-IQ2, which was quantized from the original Qwen/Qwen3.8-Flash-Next weights. Nothing was requantized or retrained here.

Usage

With the paperniuk/ds4 fork of DwarfStar (branch m1-flash-next):

hf download paperniuk/Qwen3.8-Flash-Next-MTP-block --local-dir ~/models/flash-next/mtp

M=~/models/flash-next/Q2_0
DS4_QWEN_NGRAM_GGUF=$M/Qwen3.8-Flash-Next-GSQ-RCO-Q2_0-00002-of-00002.gguf \
DS4_QWEN_MTP_GGUF=~/models/flash-next/mtp/Qwen3.8-Flash-Next-MTP-block.gguf \
./ds4-server -m $M/Qwen3.8-Flash-Next-GSQ-RCO-Q2_0-00001-of-00002.gguf \
    --ctx 262144 --prefill-chunk 2048 --mtp

Measurements

M1 Max 64 GB, ISTA Q2_0 main model, 4K context, greedy, 400 tokens. Output is identical to plain decoding in every run.

Prompt	No MTP	This block	ggml-org `mtp-...-Q8_0.gguf` (3.9 GB)
Code	34.6 tok/s	42.7 to 43.8 tok/s	43.2 tok/s
Prose	33.6 tok/s	37.9 tok/s	37.7 tok/s

First draft acceptance: 91% on code, 70% on prose. The larger Q8_0 block from ggml-org also works with the fork and is as fast; this one needs 1.2 GiB less memory.

License

Qwen Community License 1.0, the same as the original model. The full terms are in LICENSE. Read it before any commercial use.

Downloads last month: 378

GGUF

Model size

3B params

Architecture

qwen4exp

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Model tree for paperniuk/Qwen3.8-Flash-Next-MTP-block

Base model

Qwen/Qwen3.8-Flash-Next

Quantized

(431)

this model