Text Generation
MLX
Safetensors
English
Chinese
qwen3_5
mixed-precision
coding
tool-use
experimental
conversational
4-bit precision
Instructions to use Shiftedx/Qwopus3.8-27B-Coder-Flash-MLX-Balanced with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Shiftedx/Qwopus3.8-27B-Coder-Flash-MLX-Balanced with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("Shiftedx/Qwopus3.8-27B-Coder-Flash-MLX-Balanced") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use Shiftedx/Qwopus3.8-27B-Coder-Flash-MLX-Balanced with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "Shiftedx/Qwopus3.8-27B-Coder-Flash-MLX-Balanced"
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Shiftedx/Qwopus3.8-27B-Coder-Flash-MLX-Balanced" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use Shiftedx/Qwopus3.8-27B-Coder-Flash-MLX-Balanced with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "Shiftedx/Qwopus3.8-27B-Coder-Flash-MLX-Balanced"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "Shiftedx/Qwopus3.8-27B-Coder-Flash-MLX-Balanced" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8080/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Shiftedx/Qwopus3.8-27B-Coder-Flash-MLX-Balanced", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use Shiftedx/Qwopus3.8-27B-Coder-Flash-MLX-Balanced with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "Shiftedx/Qwopus3.8-27B-Coder-Flash-MLX-Balanced"
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 Shiftedx/Qwopus3.8-27B-Coder-Flash-MLX-Balanced
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Shiftedx/Qwopus3.8-27B-Coder-Flash-MLX-Balanced with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "Shiftedx/Qwopus3.8-27B-Coder-Flash-MLX-Balanced"
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 "Shiftedx/Qwopus3.8-27B-Coder-Flash-MLX-Balanced" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Download capability_validation.json from Shiftedx/Qwopus3.8-27B-Coder-Flash-MLX-Balanced: direct link, hf CLI and curl.
- Browser
- Download file 1.82 kB
-
https://huggingface.co/Shiftedx/Qwopus3.8-27B-Coder-Flash-MLX-Balanced/resolve/main/capability_validation.json
- Command line
-
hf download hf://Shiftedx/Qwopus3.8-27B-Coder-Flash-MLX-Balanced/capability_validation.json
-
curl -L -o capability_validation.json https://huggingface.co/Shiftedx/Qwopus3.8-27B-Coder-Flash-MLX-Balanced/resolve/main/capability_validation.json
1.82 kB
| { | |
| "runtime": "Kapitsa 0.2.31", | |
| "runtime_commit": "84249c0a79d6d6dd930998cce69a58b41dee586b", | |
| "host": "M4 Max, 40-core GPU, 64 GiB", | |
| "context_limit": 131072, | |
| "native_mtp_head": "mtp.safetensors", | |
| "sampler": "greedy; thinking off", | |
| "text_prompts": 4, | |
| "vision_cases": "8 generated OCR, chart, spatial and two-image cases; two seeds; unique chart maxima", | |
| "vision_fixture_seeds": [ | |
| 7319, | |
| 173 | |
| ], | |
| "normalized_grading": "Remove one enclosing Markdown JSON fence, parse JSON, require exact object/array equality. No flattening or visual-answer rewriting.", | |
| "decode_measurement": "Mean server-reported decode for one code and one prose output, 256-token cap; one run per mode.", | |
| "results": { | |
| "ar": { | |
| "text_parity_passed": 0, | |
| "text_total": 4, | |
| "vision_bare_json_passed": 4, | |
| "vision_normalized_json_passed": 8, | |
| "vision_total": 8, | |
| "code_prose_mean_decode_tps": 20.2 | |
| }, | |
| "mtp1": { | |
| "text_parity_passed": 4, | |
| "text_total": 4, | |
| "vision_bare_json_passed": 0, | |
| "vision_normalized_json_passed": 0, | |
| "vision_total": 0, | |
| "code_prose_mean_decode_tps": 29.9 | |
| }, | |
| "mtp2": { | |
| "text_parity_passed": 4, | |
| "text_total": 4, | |
| "vision_bare_json_passed": 4, | |
| "vision_normalized_json_passed": 8, | |
| "vision_total": 8, | |
| "code_prose_mean_decode_tps": 39.6 | |
| }, | |
| "mtp3": { | |
| "text_parity_passed": 4, | |
| "text_total": 4, | |
| "vision_bare_json_passed": 0, | |
| "vision_normalized_json_passed": 0, | |
| "vision_total": 0, | |
| "code_prose_mean_decode_tps": 45.5 | |
| }, | |
| "dflash2": { | |
| "text_parity_passed": 4, | |
| "text_total": 4, | |
| "vision_bare_json_passed": 4, | |
| "vision_normalized_json_passed": 8, | |
| "vision_total": 8, | |
| "code_prose_mean_decode_tps": 90.3 | |
| } | |
| } | |
| } | |