Instructions to use pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-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 pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-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 pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-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 pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF:Q4_K_M
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 pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF:Q4_K_M
Use Docker
docker model run hf.co/pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-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": "pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF:Q4_K_M
- Ollama
How to use pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF with Ollama:
ollama run hf.co/pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF:Q4_K_M
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": "pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF with Docker Model Runner:
docker model run hf.co/pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF:Q4_K_M
- Lemonade
How to use pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-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 pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-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://127.0.0.1:9931/v1 hermes config set model.default pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-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://127.0.0.1:9931/v1 \ --custom-model-id "pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-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"
MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF
GGUF conversions of lightx2v/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA.
The model rewrites user requests into structured MiniMax-H3 video and audio prompts.
These are complete model weights with a separate vision projector. Load the language
file with -m and the projector with --mmproj.
Tasks: Ref2VA with ordered image references, sampled video frames and explicit audio descriptions.
Output: subject_definitions, summary, retention_analysis, detailed_description, overall_soundscape, non_diegetic_music.
Files
| File | Download size | Contents |
|---|---|---|
| MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-Q5_K_M.gguf | 6.468 GB | Q5_K_M |
| MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-Q4_K_M.gguf | 5.629 GB | Q4_K_M |
| mmproj-MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-F16.gguf | 0.918 GB | Vision projector, F16 |
Sizes are decimal GB of files on disk. Runtime memory also includes the context, vision processing and backend allocations. Both quantizations use the same F16 projector extracted from this checkpoint.
conversion.json records source/output SHA-256 hashes and the conversion tools.
The BF16 control used for validation is not required to run these files.
ComfyUI
Install MiniMax-H3 Prompt Rewriter
and add MiniMax-H3 Qwen Rewriter with Qwen Rewriter Options. Choose this
checkpoint in Model list, or put the model and projector together under
ComfyUI/models/LLM/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF/ for local discovery.
The node provides input checkboxes, the ordered reference strip, + instr,
aspect ratio, duration, bypass/repeat and the prompt library. Its references
output carries the original enabled conditioning to Reference Slots or Reference
Encode. Select a task supported by this checkpoint.
llama.cpp
Use a build that supports qwen35 and its Qwen3-VL vision projector. Conversion
used llama.cpp commit cb26014d965036f0eacdab7387b222d28d36b9e6 (b10310).
hf download pytraveler/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-GGUF --include '*Q5_K_M.gguf' 'mmproj-*.gguf' --local-dir .
llama-server -m MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-Q5_K_M.gguf \
--mmproj mmproj-MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA-F16.gguf --jinja \
--ctx-size 32768 --n-gpu-layers 999 --host 127.0.0.1 --port 8081
Supply the matching official writing guide and task request, as in the upstream inference example. Image parts must stay interleaved with their labels. Video references are sampled images with source timestamps. The ComfyUI node builds this request automatically.
The upstream defaults are temperature=0.7, top_p=0.8, top_k=20 and
max_tokens=16384, with thinking enabled. A smaller budget can be used with
thinking disabled through chat_template_kwargs.enable_thinking=false.
Audio: this checkpoint has no audio encoder. Provide an explicit description of the reference sound. The original Ref2VA helper labels audio but does not send its waveform; these conversions do not add a hearing capability.
Validation
Q5_K_M and Q4_K_M loaded on an NVIDIA GeForce RTX 5090 and returned the task sections from image references. The original SFT also completed a smoke test (BF16 for 9B, NF4 for 27B). Exact settings, timings and H3 findings are recorded in validation.json.
Quantization changes the weights and can change the wording. A successful smoke test checks loading, media input and output structure; it is not a quality score.
Conversion and source
Source: lightx2v/MiniMax-H3-Prompt-Rewriter-Qwen3.5-9B-Ref2VA at 4b602d004317e6c7d6a9dc113bb3280835b49b71.
The official convert_hf_to_gguf.py produced a BF16 language-model control with
--no-nextn and an F16 vision projector with --mmproj from the same SFT
directory. llama-quantize produced Q5_K_M and Q4_K_M language files. The vision
projector was kept at F16; no additional LoRA is needed.
The writing guides are fetched from their original source by the node and are not redistributed in this repository.
Licence and credits
The original checkpoint includes an Apache 2.0 licence, copied here as LICENSE. Credit for the fine-tuned model belongs to LightX2V and for its base model to Qwen.
Prompt format and video generation: MiniMax-H3.
- Downloads last month
- 1,468
4-bit
5-bit