Text Generation
GGUF
English
qwen
qwen3.8
weight-editing
weight-space-programming
experimental
reasoning
conversational
Instructions to use Xananthium/Calmer-Qwen3.8-Flash-Next with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Xananthium/Calmer-Qwen3.8-Flash-Next 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 Xananthium/Calmer-Qwen3.8-Flash-Next:TQ2_0 # Run inference directly in the terminal: llama cli -hf Xananthium/Calmer-Qwen3.8-Flash-Next:TQ2_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Xananthium/Calmer-Qwen3.8-Flash-Next:TQ2_0 # Run inference directly in the terminal: llama cli -hf Xananthium/Calmer-Qwen3.8-Flash-Next:TQ2_0
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf Xananthium/Calmer-Qwen3.8-Flash-Next:TQ2_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf Xananthium/Calmer-Qwen3.8-Flash-Next:TQ2_0
Use Docker
docker model run hf.co/Xananthium/Calmer-Qwen3.8-Flash-Next:TQ2_0
- Llama new
- LM Studio
- Jan
- vLLM
How to use Xananthium/Calmer-Qwen3.8-Flash-Next with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Xananthium/Calmer-Qwen3.8-Flash-Next" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Xananthium/Calmer-Qwen3.8-Flash-Next", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Xananthium/Calmer-Qwen3.8-Flash-Next:TQ2_0
- Ollama
How to use Xananthium/Calmer-Qwen3.8-Flash-Next with Ollama:
ollama run hf.co/Xananthium/Calmer-Qwen3.8-Flash-Next:TQ2_0
- Unsloth Desktop
- Pi
How to use Xananthium/Calmer-Qwen3.8-Flash-Next with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Xananthium/Calmer-Qwen3.8-Flash-Next:TQ2_0
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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Xananthium/Calmer-Qwen3.8-Flash-Next:TQ2_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Xananthium/Calmer-Qwen3.8-Flash-Next with Docker Model Runner:
docker model run hf.co/Xananthium/Calmer-Qwen3.8-Flash-Next:TQ2_0
- Lemonade
How to use Xananthium/Calmer-Qwen3.8-Flash-Next with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Xananthium/Calmer-Qwen3.8-Flash-Next:TQ2_0
Run and chat with the model
lemonade run user.Calmer-Qwen3.8-Flash-Next-TQ2_0
List all available models
lemonade list
- Hermes Agent
How to use Xananthium/Calmer-Qwen3.8-Flash-Next with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Xananthium/Calmer-Qwen3.8-Flash-Next:TQ2_0
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://127.0.0.1:9931/v1 hermes config set model.default Xananthium/Calmer-Qwen3.8-Flash-Next:TQ2_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Xananthium/Calmer-Qwen3.8-Flash-Next with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Xananthium/Calmer-Qwen3.8-Flash-Next:TQ2_0
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://127.0.0.1:9931/v1 \ --custom-model-id "Xananthium/Calmer-Qwen3.8-Flash-Next:TQ2_0" \ --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"
Download tested_runtime.json from Xananthium/Calmer-Qwen3.8-Flash-Next: direct link, hf CLI and curl.
- Browser
- Download file 1.59 kB
-
https://huggingface.co/Xananthium/Calmer-Qwen3.8-Flash-Next/resolve/main/tested_runtime.json
- Command line
-
hf download hf://Xananthium/Calmer-Qwen3.8-Flash-Next/tested_runtime.json
-
curl -L -o tested_runtime.json https://huggingface.co/Xananthium/Calmer-Qwen3.8-Flash-Next/resolve/main/tested_runtime.json
1.59 kB
| { | |
| "engine": "Strata 0.1.59.1", | |
| "gpus": [ | |
| "NVIDIA RTX 3090", | |
| "NVIDIA RTX 3090" | |
| ], | |
| "context_tokens": 262144, | |
| "kv": "q4_0", | |
| "parallel": 4, | |
| "layer_split": 24, | |
| "mtp_tokens": 4, | |
| "spec_min_p": 0.7, | |
| "pipeline_windows": 2, | |
| "batch_groups": "auto", | |
| "sampling": { | |
| "temperature": 1.3, | |
| "top_p": 0.95, | |
| "top_k": 20, | |
| "min_p": 0.0, | |
| "presence_penalty": 0.0, | |
| "repetition_penalty": 1.0 | |
| }, | |
| "reasoning_effort": "medium", | |
| "test_max_output_tokens": 75000, | |
| "runtime_control_vector": { | |
| "file": "Huihui-Qwen3.8-Flash-Next-refusal-direction-r.gguf", | |
| "scale": 1.0, | |
| "layer_range": [ | |
| 4, | |
| 44 | |
| ], | |
| "mode": "project", | |
| "direction": "per-layer", | |
| "baked_into_release": false, | |
| "source_repo": "alesha-pro/Qwen3.8-Flash-Next-abliterated-GSQ-RCO-Strata-GGUF", | |
| "sha256": "59f9ae8b4372107ae79044278a4406bdfe8f8861fe599aa5848515f0d072be38" | |
| }, | |
| "separate_assets": [ | |
| "Compatible expert pack and tokenizer", | |
| "MTP runtime assets", | |
| "Expert residency profile", | |
| "Runtime control vector" | |
| ], | |
| "forced_endings": { | |
| "answer_room": false, | |
| "reasoning_budget_tokens": 0, | |
| "reasoning_close_retry": false, | |
| "reasoning_loop_recovery": false, | |
| "repeat_stop_tokens": 0 | |
| }, | |
| "env": { | |
| "STRATA_HC_Q8": "1", | |
| "STRATA_ROUTE_TAIL_SKIP": "0", | |
| "STRATA_GDN_TC": "1", | |
| "STRATA_GDN_CONVL2": "2", | |
| "STRATA_QSA_SPLIT_ATTN": "1", | |
| "STRATA_PW_WITH_BATCH": "1" | |
| }, | |
| "model_api_alias_in_saved_tests": "qwen3.8-27b-hauhau-q4", | |
| "alias_note": "Historical API alias; actual model was Flash-Next." | |
| } | |