Instructions to use arpicato/qwen38-27b-8plus9-splice with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use arpicato/qwen38-27b-8plus9-splice 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 arpicato/qwen38-27b-8plus9-splice:F16
# Run inference directly in the terminal:
llama cli -hf arpicato/qwen38-27b-8plus9-splice:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf arpicato/qwen38-27b-8plus9-splice:F16
# Run inference directly in the terminal:
llama cli -hf arpicato/qwen38-27b-8plus9-splice:F16

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 arpicato/qwen38-27b-8plus9-splice:F16
# Run inference directly in the terminal:
./llama-cli -hf arpicato/qwen38-27b-8plus9-splice:F16

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 arpicato/qwen38-27b-8plus9-splice:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf arpicato/qwen38-27b-8plus9-splice:F16

Use Docker

docker model run hf.co/arpicato/qwen38-27b-8plus9-splice:F16

LM Studio
Jan
Ollama
How to use arpicato/qwen38-27b-8plus9-splice with Ollama:
```
ollama run hf.co/arpicato/qwen38-27b-8plus9-splice:F16
```
Unsloth Desktop

How to use arpicato/qwen38-27b-8plus9-splice with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf arpicato/qwen38-27b-8plus9-splice:F16

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": "arpicato/qwen38-27b-8plus9-splice:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use arpicato/qwen38-27b-8plus9-splice with Docker Model Runner:
```
docker model run hf.co/arpicato/qwen38-27b-8plus9-splice:F16
```

Lemonade

How to use arpicato/qwen38-27b-8plus9-splice with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull arpicato/qwen38-27b-8plus9-splice:F16

Run and chat with the model

lemonade run user.qwen38-27b-8plus9-splice-F16

List all available models

lemonade list

Hermes Agent

How to use arpicato/qwen38-27b-8plus9-splice with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf arpicato/qwen38-27b-8plus9-splice:F16

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 arpicato/qwen38-27b-8plus9-splice:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use arpicato/qwen38-27b-8plus9-splice with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf arpicato/qwen38-27b-8plus9-splice:F16

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 "arpicato/qwen38-27b-8plus9-splice:F16" \
  --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"

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Qwen3.8 Splice Package (canonical: IQ4_XS-gate/up + F16 alpha/beta)

Package files:

spliced-iq-f16ab.gguf       # canonical build (sensitivity-guided: F16 ssm_alpha/beta)
splice-iq-f16ab-metadata.json  # provenance
spliced-iq.gguf             # previous canonical (Q8_0 alpha/beta)
splice-iq-metadata.json

On HF these are published as spliced-iq.gguf + splice-iq-metadata.json (no generic spliced.gguf name anywhere — it is not descriptive). The baseline (unsloth/Qwen3.8-27B-GGUF @ 4ca7207...) is NOT ours and is never stored here; the A/B driver fetches it from upstream (see bench/ab/run_ab_pod.sh).

Student tensor scheme (matches Unsloth per-tensor mix): Q4_K attn_gate/attn_qkv/ffn_down, IQ4_XS ffn_gate/ffn_up (their imatrix), Q5_K ssm_out, Q8_0 ssm_alpha/beta, F32 norms/bias/conv. Official llama.cpp Qwen3 V-head reorder applied to student linear-attention tensors.

Layer order:

source 0..7, student(8+9), source 10..64 shifted to output 9..63

History (all removed 2026-09-04):

spliced.gguf (F16 student, +342 MB over baseline) — void comparison.
spliced-q4k.gguf (Q4_K-only student) — valid A/B 290/548 vs baseline 315/548, recorded in results/ab-20260903T195909Z/ARTIFACT.md, HF commit ed9fc71bad7719806ec252a8eaafe667673688fe.
baseline.gguf — byte-identical Unsloth copy, not a result.

Verify uploads:

sha256sum -c SHA256SUMS

The spliced files retain raw GGUF tensor payloads for untouched source tensors. Student matmuls are quantized to match the baseline scheme (Q4_K modal; ssm_out Q5_K; ssm_alpha/beta Q8_0; norms/bias/conv F32). The -iq variant uses IQ4_XS (with unsloth's imatrix) for ffn_gate/ffn_up, mirroring the baseline's per-tensor mix. Official llama.cpp Qwen3 V-head reorder is applied to student linear-attention tensors.

Layer order:

source 0..7, student(8+9), source 10..64 shifted to output 9..63

spliced.gguf was removed 2026-09-04 (old F16-student build, superseded)
baseline.gguf was removed 2026-09-04 — it is the Unsloth source artifact, not ours; fetch it from unsloth/Qwen3.8-27B-GGUF revision 4ca720788d1e01f1bff70c033e0d0028fd02e502. The A/B driver does this automatically (see bench/ab/run_ab_pod.sh).

Verify uploads:

sha256sum -c SHA256SUMS

Downloads last month: 4,374

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

16-bit

View +1 variant

Inference Providers NEW

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