Instructions to use 6block/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 6block/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 6block/Qwen3.8-Flash-Next-GGUF:IQ1_M
# Run inference directly in the terminal:
llama cli -hf 6block/Qwen3.8-Flash-Next-GGUF:IQ1_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf 6block/Qwen3.8-Flash-Next-GGUF:IQ1_M
# Run inference directly in the terminal:
llama cli -hf 6block/Qwen3.8-Flash-Next-GGUF:IQ1_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 6block/Qwen3.8-Flash-Next-GGUF:IQ1_M
# Run inference directly in the terminal:
./llama-cli -hf 6block/Qwen3.8-Flash-Next-GGUF:IQ1_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 6block/Qwen3.8-Flash-Next-GGUF:IQ1_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf 6block/Qwen3.8-Flash-Next-GGUF:IQ1_M

Use Docker

docker model run hf.co/6block/Qwen3.8-Flash-Next-GGUF:IQ1_M

LM Studio
Jan

vLLM

How to use 6block/Qwen3.8-Flash-Next-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "6block/Qwen3.8-Flash-Next-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": "6block/Qwen3.8-Flash-Next-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/6block/Qwen3.8-Flash-Next-GGUF:IQ1_M

Ollama
How to use 6block/Qwen3.8-Flash-Next-GGUF with Ollama:
```
ollama run hf.co/6block/Qwen3.8-Flash-Next-GGUF:IQ1_M
```
Unsloth Desktop

How to use 6block/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 6block/Qwen3.8-Flash-Next-GGUF:IQ1_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": "6block/Qwen3.8-Flash-Next-GGUF:IQ1_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use 6block/Qwen3.8-Flash-Next-GGUF with Docker Model Runner:
```
docker model run hf.co/6block/Qwen3.8-Flash-Next-GGUF:IQ1_M
```

Lemonade

How to use 6block/Qwen3.8-Flash-Next-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull 6block/Qwen3.8-Flash-Next-GGUF:IQ1_M

Run and chat with the model

lemonade run user.Qwen3.8-Flash-Next-GGUF-IQ1_M

List all available models

lemonade list

Hermes Agent

How to use 6block/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 6block/Qwen3.8-Flash-Next-GGUF:IQ1_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 6block/Qwen3.8-Flash-Next-GGUF:IQ1_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use 6block/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 6block/Qwen3.8-Flash-Next-GGUF:IQ1_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 "6block/Qwen3.8-Flash-Next-GGUF:IQ1_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"

Qwen3.8-Flash-Next GGUF

GGUF quantizations of Qwen/Qwen3.8-Flash-Next, made with llama.cpp.

Chinese version: README_zh.md

180B total parameters. A MoE core of 125B (48 layers, 512 experts, top-10 plus one shared expert) plus a 51B PLE n-gram lookup table. Hybrid attention: Gated DeltaNet linear attention interleaved with Qwen Sparse Attention (QSA) blocks, wrapped in hyper-connections. Context length up to 262K. The one MTP draft layer in the checkpoint is excluded at conversion time.

Quantized from the official BF16 weights. Every tier is imatrix-calibrated and ships as 8 shards.

Quantizations

Quant	Size	Shards	BPW	PPL (wikitext-2)
BF16 master	329.7 GiB	8	15.73	1.7164 ± 0.04795
`IQ4_XS`	118.8 GiB	8	5.67	1.8378 ± 0.05554
`IQ3_XXS`	107.4 GiB	8	5.13	2.0528 ± 0.06396
`IQ2_XS-layered`	83.5 GiB	8	3.98	2.7833 ± 0.10058
`IQ1_M-layered`	76.4 GiB	8	3.65	4.4105 ± 0.19322

The master row is not a file in this repo. It is listed so the numbers above have a reference point — the BF16 master fits on the PPL machine, so tiers are compared against a real baseline.

The two low tiers use layered quantization (IQ2_XS-layered, IQ1_M-layered): the 51B PLE n-gram table tolerates heavy compression (measured: Q8_0 → Q4_0 costs nothing), so it is packed at Q4_0, and the space saved is spent on the expert gate/up projections instead — which improves PPL by ~14% at a smaller file size than the uniform tier. High tiers stay uniform since they already sit close to the master.

What is protected

The layers that would hurt most under low-bit compression are kept at higher precision:

Tensors	Type	Reason
`ffn_gate_inp` / `ffn_gate_inp_shexp`	F32	MoE router; compressing it routes to the wrong experts
`ffn_*_shexp`	Q8_0	the shared expert runs on every token
`ssm_a` / `ssm_conv1d` / `ssm_dt` / `ssm_alpha` / `ssm_beta` / `ssm_norm` / `ssm_out`	F32	Gated DeltaNet linear-attention state; low bit-width destroys long-range recall
`hc_attn_` / `hc_ffn_` / `output_hc_*`	F32	hyper-connection streams, every layer
`ple_key` / `ple_value` / `ple_conv1d`	Q8_0	PLE projection layers
`per_layer_token_embd` (51B n-gram table)	Q4_0	n-gram counts, highly compression-tolerant
`token_embd` / `output`	Q6_K	a global type would otherwise squeeze these hard

With 512 experts the expert layers dominate the file, so protecting everything else is cheap.

Usage

# Point at the first shard; llama.cpp finds the rest on its own.
llama-cli -m Qwen3.8-Flash-Next-IQ4_XS-00001-of-00008.gguf

Do not pass -ngl manually — llama.cpp fits layers to free VRAM by itself, and any explicit -ngl aborts that fitting. Leave it off.

Every tier ships as 8 shards. Download all 8 into one directory — you only ever name -00001-of-00008 on the command line.

About the PPL numbers

wikitext-2 test, n_ctx=512, 12 chunks, every tier through the exact same command. These numbers are only comparable within this table. Do not compare them against PPL figures published by other repos.

The BF16 master row is the measured baseline. IQ2_XS-layered / IQ1_M-layered use layered quantization (see above) — at the same size they beat the uniform tiers by a wide margin.

License

Qwen Community License 1.0, inherited from Qwen/Qwen3.8-Flash-Next — this is not MIT. Quantized by 6block.

Downloads last month: -

GGUF

Model size

177B params

Architecture

qwen4exp

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

Model tree for 6block/Qwen3.8-Flash-Next-GGUF

Base model

Qwen/Qwen3.8-Flash-Next

Quantized

(158)

this model

Collection including 6block/Qwen3.8-Flash-Next-GGUF

Qwen3.8

Collection

Qwen3.8-27B (dense, vision) imatrix GGUF: 18 tiers plus q8_0/f16 mmproj and an MTP draft. More Qwen3.8 sizes as they land. • 2 items • Updated about 7 hours ago