Instructions to use TheStageAI/Qwen3.5-9B-GGUF 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 TheStageAI/Qwen3.5-9B-GGUF 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 TheStageAI/Qwen3.5-9B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf TheStageAI/Qwen3.5-9B-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf TheStageAI/Qwen3.5-9B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf TheStageAI/Qwen3.5-9B-GGUF:Q4_K_M
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 TheStageAI/Qwen3.5-9B-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf TheStageAI/Qwen3.5-9B-GGUF:Q4_K_M
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 TheStageAI/Qwen3.5-9B-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf TheStageAI/Qwen3.5-9B-GGUF:Q4_K_M
Use Docker
docker model run hf.co/TheStageAI/Qwen3.5-9B-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use TheStageAI/Qwen3.5-9B-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TheStageAI/Qwen3.5-9B-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TheStageAI/Qwen3.5-9B-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/TheStageAI/Qwen3.5-9B-GGUF:Q4_K_M
- Ollama
How to use TheStageAI/Qwen3.5-9B-GGUF with Ollama:
ollama run hf.co/TheStageAI/Qwen3.5-9B-GGUF:Q4_K_M
- Unsloth Studio
How to use TheStageAI/Qwen3.5-9B-GGUF 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 TheStageAI/Qwen3.5-9B-GGUF 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 TheStageAI/Qwen3.5-9B-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for TheStageAI/Qwen3.5-9B-GGUF to start chatting
- Pi
How to use TheStageAI/Qwen3.5-9B-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf TheStageAI/Qwen3.5-9B-GGUF:Q4_K_M
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": "TheStageAI/Qwen3.5-9B-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use TheStageAI/Qwen3.5-9B-GGUF with Docker Model Runner:
docker model run hf.co/TheStageAI/Qwen3.5-9B-GGUF:Q4_K_M
- Lemonade
How to use TheStageAI/Qwen3.5-9B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull TheStageAI/Qwen3.5-9B-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Qwen3.5-9B-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use TheStageAI/Qwen3.5-9B-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf TheStageAI/Qwen3.5-9B-GGUF:Q4_K_M
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 TheStageAI/Qwen3.5-9B-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use TheStageAI/Qwen3.5-9B-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf TheStageAI/Qwen3.5-9B-GGUF:Q4_K_M
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 "TheStageAI/Qwen3.5-9B-GGUF:Q4_K_M" \ --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"
| { | |
| "artifact_scope": "language_model_gguf", | |
| "base_model": "Qwen/Qwen3.5-9B", | |
| "base_model_revision": "c202236235762e1c871ad0ccb60c8ee5ba337b9a", | |
| "benchmark_protocols": { | |
| "ifeval": { | |
| "decoding": "temperature=0", | |
| "mode": "native chat, enable_thinking=false", | |
| "sample_count": 541 | |
| }, | |
| "mmlu_pro": { | |
| "backend": "vllm", | |
| "dataset_revision": "b189ec765aa7ed75c8acfea42df31fdae71f97be", | |
| "decoding": "temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, frequency_penalty=0.0, repetition_penalty=1.0, seed=42", | |
| "enable_prefix_caching": false, | |
| "enable_thinking": true, | |
| "language_model_only": true, | |
| "max_model_len": 40960, | |
| "max_new_tokens": 32768, | |
| "mode": "native_chat, enable_thinking=true", | |
| "ntrain": 0, | |
| "prompt_format": "native_chat", | |
| "prompt_template_id": "qwen_mc_json_v1", | |
| "protocol": "mmlu_pro_cardlike_thinking_v2", | |
| "sample_count": 12032, | |
| "sampling": { | |
| "frequency_penalty": 0.0, | |
| "min_p": 0.0, | |
| "presence_penalty": 1.5, | |
| "repetition_penalty": 1.0, | |
| "seed": 42, | |
| "temperature": 1.0, | |
| "top_k": 20, | |
| "top_p": 0.95 | |
| }, | |
| "stop_sequences": [], | |
| "system_prompt": null | |
| } | |
| }, | |
| "bf16_reference": { | |
| "ifeval": { | |
| "instruction_loose": 0.9148681055155875, | |
| "instruction_strict": 0.8836930455635491, | |
| "prompt_loose": 0.8761552680221811, | |
| "prompt_strict": 0.8317929759704251, | |
| "run_id": "release_20260715_bf16_ifeval_public1280_v1_qwen3p5_9b_bf16_lm_eval", | |
| "sample_count": 541, | |
| "status": "complete" | |
| }, | |
| "mmlu_pro": { | |
| "accuracy": 0.8238863031914894, | |
| "correct": 9913, | |
| "not_reported_reason": null, | |
| "run_id": "release_20260715_bf16_qwen35_mmlu_pro_cardlike_v2_qwen3p5_9b_bf16_mmlu_pro_official", | |
| "sample_count": 12032, | |
| "status": "complete" | |
| } | |
| }, | |
| "display_name": "Qwen3.5 9B", | |
| "family": "Qwen 3.5", | |
| "generated_at": "2026-07-21T17:43:34.621255+00:00", | |
| "license": "apache-2.0", | |
| "model_key": "qwen3p5_9b", | |
| "reasoning_policy": { | |
| "reasoning_products": [ | |
| "S", | |
| "M", | |
| "L" | |
| ], | |
| "xs": "non_thinking_only" | |
| }, | |
| "recommended_product": "M", | |
| "recommended_quality": { | |
| "metric": "ifeval_instruction_strict", | |
| "ratio_to_bf16": 1.0013568521031209, | |
| "retention_percent_display": 100 | |
| }, | |
| "repo_id": "TheStageAI/Qwen3.5-9B-GGUF", | |
| "schema": "thestageai.gguf_release_manifest_v3", | |
| "tested_llama_cpp_revision": "bec4772f6a2527d371557b5d2032641e5ff7619c", | |
| "variants": [ | |
| { | |
| "benchmarks": { | |
| "ifeval": { | |
| "instruction_loose": 0.8741007194244604, | |
| "instruction_strict": 0.8513189448441247, | |
| "prompt_loose": 0.8207024029574861, | |
| "prompt_strict": 0.7929759704251387, | |
| "run_id": "release_20260715_quant_ifeval_public1280_v1_qwen3p5_9b_xs_lm_eval", | |
| "sample_count": 541, | |
| "status": "complete" | |
| }, | |
| "mmlu_pro": { | |
| "accuracy": null, | |
| "correct": null, | |
| "not_reported_reason": "unstable_long_thinking_behavior", | |
| "run_id": null, | |
| "sample_count": null, | |
| "status": "not_reported" | |
| } | |
| }, | |
| "evaluation_id": "b6572505298fac3b95b7af5fa8cfb8a4928bd3273fbca47f91af7c945302d35a", | |
| "file_bytes": 3206390080, | |
| "filename": "Qwen3.5-9B-XS-TS-Q3_K_S.gguf", | |
| "gguf_file_type": "MOSTLY_Q2_K", | |
| "heldout_kl_mean": 0.13765087766881626, | |
| "hub_quant_label": "Q3_K_S", | |
| "hub_size_class": "3-bit", | |
| "lm_head_policy": "emit_output", | |
| "output_embedding_mode": "independent", | |
| "parameter_count": 8953803264, | |
| "positioning": "Minimum footprint", | |
| "product": "XS", | |
| "reasoning_support": "non_thinking_only", | |
| "recommended": false, | |
| "schedule_method": "RCO anchor", | |
| "sha256": "b278499cf1e90cf6c72704dcf588c6dc4db114ecd837caf203749a0f72501567", | |
| "tensor_count": 427, | |
| "tensor_type_counts": { | |
| "BF16": 48, | |
| "F32": 177, | |
| "Q2_K": 178, | |
| "Q3_K": 22, | |
| "Q4_K": 2 | |
| }, | |
| "whole_file_bpw": 2.864829601866937 | |
| }, | |
| { | |
| "benchmarks": { | |
| "ifeval": { | |
| "instruction_loose": 0.9004796163069544, | |
| "instruction_strict": 0.8764988009592326, | |
| "prompt_loose": 0.8558225508317929, | |
| "prompt_strict": 0.8280961182994455, | |
| "run_id": "release_20260715_quant_ifeval_public1280_v1_qwen3p5_9b_s_lm_eval", | |
| "sample_count": 541, | |
| "status": "complete" | |
| }, | |
| "mmlu_pro": { | |
| "accuracy": 0.7970412234042553, | |
| "correct": 9590, | |
| "not_reported_reason": null, | |
| "run_id": "release_20260715_quant_qwen35_mmlu_pro_cardlike_v2_qwen3p5_9b_s_mmlu_pro_official", | |
| "sample_count": 12032, | |
| "status": "complete" | |
| } | |
| }, | |
| "evaluation_id": "c3a6b4dd462f98074646695a06c1ab3f812798b5f58eab63cf8832cba5f2ff27", | |
| "file_bytes": 4094812448, | |
| "filename": "Qwen3.5-9B-S-TS-Q4_K_S.gguf", | |
| "gguf_file_type": "MOSTLY_Q2_K", | |
| "heldout_kl_mean": 0.05430385740619881, | |
| "hub_quant_label": "Q4_K_S", | |
| "hub_size_class": "4-bit", | |
| "lm_head_policy": "emit_output", | |
| "output_embedding_mode": "independent", | |
| "parameter_count": 8953803264, | |
| "positioning": "Compact", | |
| "product": "S", | |
| "reasoning_support": "supported", | |
| "recommended": false, | |
| "schedule_method": "RCO anchor", | |
| "sha256": "27c46cb7741a8ac63fb330192aed82b5582d61dce4d42bbc5ac55ee1453d484f", | |
| "tensor_count": 427, | |
| "tensor_type_counts": { | |
| "BF16": 48, | |
| "F32": 177, | |
| "Q2_K": 44, | |
| "Q3_K": 92, | |
| "Q4_K": 49, | |
| "Q5_K": 14, | |
| "Q6_K": 3 | |
| }, | |
| "whole_file_bpw": 3.658612839496939 | |
| }, | |
| { | |
| "benchmarks": { | |
| "ifeval": { | |
| "instruction_loose": 0.9160671462829736, | |
| "instruction_strict": 0.8848920863309353, | |
| "prompt_loose": 0.8761552680221811, | |
| "prompt_strict": 0.833641404805915, | |
| "run_id": "release_20260715_quant_ifeval_public1280_v1_qwen3p5_9b_m_lm_eval", | |
| "sample_count": 541, | |
| "status": "complete" | |
| }, | |
| "mmlu_pro": { | |
| "accuracy": 0.8215591755319149, | |
| "correct": 9885, | |
| "not_reported_reason": null, | |
| "run_id": "release_20260715_quant_qwen35_mmlu_pro_cardlike_v2_qwen3p5_9b_m_mmlu_pro_official", | |
| "sample_count": 12032, | |
| "status": "complete" | |
| } | |
| }, | |
| "evaluation_id": "2e558634b88068f1953d65f116a0780aa119935f0b93950f7027db022e37a6cf", | |
| "file_bytes": 5060174144, | |
| "filename": "Qwen3.5-9B-M-TS-Q4_K_M.gguf", | |
| "gguf_file_type": "MOSTLY_Q4_K_M", | |
| "heldout_kl_mean": 0.01154941470606636, | |
| "hub_quant_label": "Q4_K_M", | |
| "hub_size_class": "4-bit", | |
| "lm_head_policy": "emit_output", | |
| "output_embedding_mode": "independent", | |
| "parameter_count": 8953803264, | |
| "positioning": "Balanced", | |
| "product": "M", | |
| "reasoning_support": "supported", | |
| "recommended": true, | |
| "schedule_method": "fixed Q4_K_M", | |
| "sha256": "f41c0a0c0e43bf721fb2da29374cd1a97271bac0bab08a9dc42964525e82350c", | |
| "tensor_count": 427, | |
| "tensor_type_counts": { | |
| "BF16": 48, | |
| "F32": 177, | |
| "Q4_K": 202 | |
| }, | |
| "whole_file_bpw": 4.52113944861409 | |
| }, | |
| { | |
| "benchmarks": { | |
| "ifeval": { | |
| "instruction_loose": 0.9112709832134293, | |
| "instruction_strict": 0.8788968824940048, | |
| "prompt_loose": 0.8743068391866913, | |
| "prompt_strict": 0.8299445471349353, | |
| "run_id": "release_20260715_quant_ifeval_public1280_v1_qwen3p5_9b_l_lm_eval", | |
| "sample_count": 541, | |
| "status": "complete" | |
| }, | |
| "mmlu_pro": { | |
| "accuracy": 0.823969414893617, | |
| "correct": 9914, | |
| "not_reported_reason": null, | |
| "run_id": "release_20260715_quant_qwen35_mmlu_pro_cardlike_v2_qwen3p5_9b_l_mmlu_pro_official", | |
| "sample_count": 12032, | |
| "status": "complete" | |
| } | |
| }, | |
| "evaluation_id": "b94c73423458c9755973adb81944b6bc2a95e49aad3ed434dd60fa121cfc4d66", | |
| "file_bytes": 9533399360, | |
| "filename": "Qwen3.5-9B-L-TS-Q8_0.gguf", | |
| "gguf_file_type": "MOSTLY_Q8_0", | |
| "heldout_kl_mean": 0.0006207412321914634, | |
| "hub_quant_label": "Q8_0", | |
| "hub_size_class": "8-bit", | |
| "lm_head_policy": "emit_output", | |
| "output_embedding_mode": "independent", | |
| "parameter_count": 8953803264, | |
| "positioning": "High-precision Q8", | |
| "product": "L", | |
| "reasoning_support": "supported", | |
| "recommended": false, | |
| "schedule_method": "fixed Q8_0", | |
| "sha256": "b3ebcfb4596bd538ff331d5f4d015456283cccb9ccc6f043746e59a99ff4da8a", | |
| "tensor_count": 427, | |
| "tensor_type_counts": { | |
| "BF16": 48, | |
| "F32": 177, | |
| "Q8_0": 202 | |
| }, | |
| "whole_file_bpw": 8.517854662570349 | |
| } | |
| ] | |
| } | |