Instructions to use YTan2000/Qwen3.8-27B-TQ3_4S with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use YTan2000/Qwen3.8-27B-TQ3_4S 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 YTan2000/Qwen3.8-27B-TQ3_4S:BF16
# Run inference directly in the terminal:
llama cli -hf YTan2000/Qwen3.8-27B-TQ3_4S:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf YTan2000/Qwen3.8-27B-TQ3_4S:BF16
# Run inference directly in the terminal:
llama cli -hf YTan2000/Qwen3.8-27B-TQ3_4S:BF16

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 YTan2000/Qwen3.8-27B-TQ3_4S:BF16
# Run inference directly in the terminal:
./llama-cli -hf YTan2000/Qwen3.8-27B-TQ3_4S:BF16

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 YTan2000/Qwen3.8-27B-TQ3_4S:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf YTan2000/Qwen3.8-27B-TQ3_4S:BF16

Use Docker

docker model run hf.co/YTan2000/Qwen3.8-27B-TQ3_4S:BF16

LM Studio
Jan

vLLM

How to use YTan2000/Qwen3.8-27B-TQ3_4S with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YTan2000/Qwen3.8-27B-TQ3_4S"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YTan2000/Qwen3.8-27B-TQ3_4S",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/YTan2000/Qwen3.8-27B-TQ3_4S:BF16

Ollama
How to use YTan2000/Qwen3.8-27B-TQ3_4S with Ollama:
```
ollama run hf.co/YTan2000/Qwen3.8-27B-TQ3_4S:BF16
```

Unsloth Studio

How to use YTan2000/Qwen3.8-27B-TQ3_4S with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for YTan2000/Qwen3.8-27B-TQ3_4S to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for YTan2000/Qwen3.8-27B-TQ3_4S to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for YTan2000/Qwen3.8-27B-TQ3_4S to start chatting

How to use YTan2000/Qwen3.8-27B-TQ3_4S with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf YTan2000/Qwen3.8-27B-TQ3_4S:BF16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "YTan2000/Qwen3.8-27B-TQ3_4S:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use YTan2000/Qwen3.8-27B-TQ3_4S with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf YTan2000/Qwen3.8-27B-TQ3_4S:BF16

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 "YTan2000/Qwen3.8-27B-TQ3_4S:BF16" \
  --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"

Docker Model Runner
How to use YTan2000/Qwen3.8-27B-TQ3_4S with Docker Model Runner:
```
docker model run hf.co/YTan2000/Qwen3.8-27B-TQ3_4S:BF16
```

Lemonade

How to use YTan2000/Qwen3.8-27B-TQ3_4S with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull YTan2000/Qwen3.8-27B-TQ3_4S:BF16

Run and chat with the model

lemonade run user.Qwen3.8-27B-TQ3_4S-BF16

List all available models

lemonade list

Hermes Agent

How to use YTan2000/Qwen3.8-27B-TQ3_4S with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf YTan2000/Qwen3.8-27B-TQ3_4S:BF16

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 YTan2000/Qwen3.8-27B-TQ3_4S:BF16

Run Hermes

hermes

Atomic Chat

YTan2000 commited on 1 day ago

Commit

337fd81

verified ·

1 Parent(s): af2bbe2

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +10 -10

README.md CHANGED Viewed

@@ -76,11 +76,11 @@ Validated on NVIDIA RTX 3090 (24 GB), single stream, draft-MTP speculative decod
 | HumanEval+ | 88.4 | official scorer, pass@1 |
 | MBPP | 90.5 | official scorer, pass@1 |
 | MBPP+ | 77.2 | official scorer, pass@1 |
-| BenchLoop coding | 93.8 | |
-| BenchLoop reason-math | 86.7 | |
-| BenchLoop toolcall | 81.7 | |
-| BenchLoop data-extract | 80.2 | |
-| BenchLoop instruct-follow | 62.2 | |
 Model size: 13.8 GB (4.24 BPW).
@@ -102,11 +102,11 @@ The 3.8's MTP head is better trained than the 3.6's (acceptance 0.849 vs 0.796),
 | Size (GB) | 13.39 GiB | 13.8 |
 | Warm long-output decode | 59.0 tok/s | **64.78 tok/s** |
 | Hard86 | 76/86 (88.4%) | 74/86 (86.0%) |
-| BenchLoop coding (EasyCode) | 100% | 93.8% |
-| BenchLoop toolcall | 96.67% | 81.7% |
-| BenchLoop data-extract | 90.97% | 80.2% |
-| BenchLoop instruct-follow | 76.67% | 62.2% |
-| BenchLoop reason-math | 73.33% | **86.7%** |
 | Draft-MTP acceptance | 0.796 | **0.849** |
 Notes on the comparison: the 3.6 column is the published model-card number (run under that model's own tuned serving config). The 3.8 column is a first-pass battery — Hard86, task suites and speed under reasoning-off; evalplus under budget-256. The 3.8 wins decisively on decode speed, MTP acceptance and reason-math; on the task suites the 3.6's tuned-config numbers remain the reference until the 3.8 battery is re-tuned.

 | HumanEval+ | 88.4 | official scorer, pass@1 |
 | MBPP | 90.5 | official scorer, pass@1 |
 | MBPP+ | 77.2 | official scorer, pass@1 |
+| Coding suite | 93.8 | |
+| Reason-math suite | 86.7 | |
+| Tool-call suite | 81.7 | |
+| Data-extract suite | 80.2 | |
+| Instruction-follow suite | 62.2 | |
 Model size: 13.8 GB (4.24 BPW).
 | Size (GB) | 13.39 GiB | 13.8 |
 | Warm long-output decode | 59.0 tok/s | **64.78 tok/s** |
 | Hard86 | 76/86 (88.4%) | 74/86 (86.0%) |
+| Coding suite | 100% | 93.8% |
+| Tool-call suite | 96.67% | 81.7% |
+| Data-extract suite | 90.97% | 80.2% |
+| Instruction-follow suite | 76.67% | 62.2% |
+| Reason-math suite | 73.33% | **86.7%** |
 | Draft-MTP acceptance | 0.796 | **0.849** |
 Notes on the comparison: the 3.6 column is the published model-card number (run under that model's own tuned serving config). The 3.8 column is a first-pass battery — Hard86, task suites and speed under reasoning-off; evalplus under budget-256. The 3.8 wins decisively on decode speed, MTP acceptance and reason-math; on the task suites the 3.6's tuned-config numbers remain the reference until the 3.8 battery is re-tuned.