Instructions to use jcbtc/Qwen3.8-27B-IU4-Kairic-Edge with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use jcbtc/Qwen3.8-27B-IU4-Kairic-Edge 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 jcbtc/Qwen3.8-27B-IU4-Kairic-Edge
# Run inference directly in the terminal:
llama cli -hf jcbtc/Qwen3.8-27B-IU4-Kairic-Edge

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jcbtc/Qwen3.8-27B-IU4-Kairic-Edge
# Run inference directly in the terminal:
llama cli -hf jcbtc/Qwen3.8-27B-IU4-Kairic-Edge

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 jcbtc/Qwen3.8-27B-IU4-Kairic-Edge
# Run inference directly in the terminal:
./llama-cli -hf jcbtc/Qwen3.8-27B-IU4-Kairic-Edge

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 jcbtc/Qwen3.8-27B-IU4-Kairic-Edge
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jcbtc/Qwen3.8-27B-IU4-Kairic-Edge

Use Docker

docker model run hf.co/jcbtc/Qwen3.8-27B-IU4-Kairic-Edge

LM Studio
Jan

vLLM

How to use jcbtc/Qwen3.8-27B-IU4-Kairic-Edge with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jcbtc/Qwen3.8-27B-IU4-Kairic-Edge"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jcbtc/Qwen3.8-27B-IU4-Kairic-Edge",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jcbtc/Qwen3.8-27B-IU4-Kairic-Edge

Ollama
How to use jcbtc/Qwen3.8-27B-IU4-Kairic-Edge with Ollama:
```
ollama run hf.co/jcbtc/Qwen3.8-27B-IU4-Kairic-Edge
```
Unsloth Desktop

How to use jcbtc/Qwen3.8-27B-IU4-Kairic-Edge with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jcbtc/Qwen3.8-27B-IU4-Kairic-Edge

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": "jcbtc/Qwen3.8-27B-IU4-Kairic-Edge"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use jcbtc/Qwen3.8-27B-IU4-Kairic-Edge with Docker Model Runner:
```
docker model run hf.co/jcbtc/Qwen3.8-27B-IU4-Kairic-Edge
```

Lemonade

How to use jcbtc/Qwen3.8-27B-IU4-Kairic-Edge with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jcbtc/Qwen3.8-27B-IU4-Kairic-Edge

Run and chat with the model

lemonade run user.Qwen3.8-27B-IU4-Kairic-Edge-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use jcbtc/Qwen3.8-27B-IU4-Kairic-Edge with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jcbtc/Qwen3.8-27B-IU4-Kairic-Edge

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 jcbtc/Qwen3.8-27B-IU4-Kairic-Edge

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use jcbtc/Qwen3.8-27B-IU4-Kairic-Edge with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jcbtc/Qwen3.8-27B-IU4-Kairic-Edge

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 "jcbtc/Qwen3.8-27B-IU4-Kairic-Edge" \
  --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"

jcbtc commited on 29 days ago

Commit

42de3b6

verified ·

1 Parent(s): ce6cdf5

Add model card

Browse files

Files changed (1) hide show

README.md +15 -4

README.md CHANGED Viewed

@@ -200,7 +200,7 @@ sudo apt-get install -y build-essential cmake git ninja-build pkg-config libssl-
 git clone https://github.com/ciru-ai/ROCmFPX.git
 cd ROCmFPX
-git checkout kairic-edge-qwen38-27b-v1
 git clone https://github.com/ROCm/composable_kernel.git third_party/composable_kernel
 git -C third_party/composable_kernel checkout fdf4bb7fcc984811cef48ce817d89aac064b984a
@@ -238,7 +238,7 @@ cmake --build build-kairic --target llama-server -j"$(nproc)"
 ./build-kairic/bin/llama-server --help | grep -A1 -- '--kairic-edge'
 ```
-See the release repository's [build and verification guide](https://github.com/ciru-ai/ROCmFPX/blob/kairic-edge-qwen38-27b-v1/docs/kairic-edge-gfx1151.md) for dependency checks, exact compiler identity, and smoke tests.
 ## Recommended launch
@@ -273,7 +273,16 @@ reasoning            off
 metrics              enabled
 ```
-For a normal non-thinking chat, keep the runtime configuration and override sampling per request with Qwen's recommended live values:
 ```bash
 curl http://127.0.0.1:8080/v1/chat/completions \
@@ -288,9 +297,11 @@ curl http://127.0.0.1:8080/v1/chat/completions \
     "presence_penalty": 1.5,
     "cache_prompt": true,
     "stream": true
-  }'
 ```
 For benchmark reproduction, keep the launcher's deterministic sampler and use the first trajectory only. Do not compare results collected with repair retries or a different chat template.
 ## Scope and limitations

 git clone https://github.com/ciru-ai/ROCmFPX.git
 cd ROCmFPX
+git checkout kairic-edge-qwen38-27b-v1.1
 git clone https://github.com/ROCm/composable_kernel.git third_party/composable_kernel
 git -C third_party/composable_kernel checkout fdf4bb7fcc984811cef48ce817d89aac064b984a
 ./build-kairic/bin/llama-server --help | grep -A1 -- '--kairic-edge'
 ```
+See the release repository's [build and verification guide](https://github.com/ciru-ai/ROCmFPX/blob/kairic-edge-qwen38-27b-v1.1/docs/kairic-edge-gfx1151.md) for dependency checks, exact compiler identity, compatibility mode, and smoke tests.
 ## Recommended launch
 metrics              enabled
 ```
+The default is the highest-throughput fast greedy mode. It accepts one unmodified greedy completion (`temperature: 0`, `top_p: 1`, `top_k: 0` or `1`, `min_p: 0`) and rejects sampling, penalties, probabilities, grammar-constrained tool calls, logit bias, LoRA, and reasoning budgets because those features require full target logits.
+For sampling, penalties, DSH, or tool calling, restart the runner with compatibility mode enabled:
+```bash
+export KAIRIC_EDGE_COMPATIBILITY_MODE=1
+./ROCmFPX/scripts/run-kairic-edge-gfx1151.sh
+```
+Then use Qwen's recommended live values at request level:
 ```bash
 curl http://127.0.0.1:8080/v1/chat/completions \
     "presence_penalty": 1.5,
     "cache_prompt": true,
     "stream": true
+}'
 ```
+Compatibility mode disables only the target greedy argmax fast path. Kairic Edge, native MTP4, prompt caching, context checkpoints, and the rest of the recommended live configuration stay enabled. In our quick release gate, sampled chat and a forced tool call both returned HTTP 200; HumanEval 0–9 passed 10/10 Base and 10/10 Plus in both modes with byte-identical raw output. Compatibility measured 41.87 versus 46.37 generated tokens/s on that short coding subset, a 9.70% reduction, so it remains opt-in. This ten-task run is a compatibility smoke test, not a leaderboard score or a universal throughput estimate.
 For benchmark reproduction, keep the launcher's deterministic sampler and use the first trajectory only. Do not compare results collected with repair retries or a different chat template.
 ## Scope and limitations