Image-Text-to-Text
MLX
Safetensors
mistral3
jangtq
mxtq
jang
apple-silicon
ministral3
pixtral
vision
multimodal
quantized
conversational
Instructions to use OsaurusAI/Mistral-Medium-3.5-128B-JANGTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use OsaurusAI/Mistral-Medium-3.5-128B-JANGTQ with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("OsaurusAI/Mistral-Medium-3.5-128B-JANGTQ") config = load_config("OsaurusAI/Mistral-Medium-3.5-128B-JANGTQ") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
- Pi new
How to use OsaurusAI/Mistral-Medium-3.5-128B-JANGTQ with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "OsaurusAI/Mistral-Medium-3.5-128B-JANGTQ"
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "OsaurusAI/Mistral-Medium-3.5-128B-JANGTQ" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use OsaurusAI/Mistral-Medium-3.5-128B-JANGTQ 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 "OsaurusAI/Mistral-Medium-3.5-128B-JANGTQ"
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 OsaurusAI/Mistral-Medium-3.5-128B-JANGTQ
Run Hermes
hermes
| { | |
| "dim": 12288, | |
| "n_layers": 88, | |
| "head_dim": 128, | |
| "hidden_dim": 28672, | |
| "n_heads": 96, | |
| "n_kv_heads": 8, | |
| "rope_theta": 1000000.0, | |
| "norm_eps": 1e-05, | |
| "vocab_size": 131072, | |
| "tied_embeddings": false, | |
| "max_position_embeddings": 262144, | |
| "llama_4_scaling": null, | |
| "q_lora_rank": null, | |
| "qk_rope_head_dim": null, | |
| "qk_nope_head_dim": null, | |
| "kv_lora_rank": null, | |
| "v_head_dim": null, | |
| "quantization": { | |
| "qformat_weight": "fp8_e4m3", | |
| "qscheme_act": "TENSOR" | |
| }, | |
| "yarn": { | |
| "original_max_position_embeddings": 4096, | |
| "factor": 64, | |
| "apply_scale": true, | |
| "beta": 4, | |
| "alpha": 1 | |
| }, | |
| "moe": null, | |
| "vision_encoder": { | |
| "image_token_id": 10, | |
| "image_break_token_id": -1, | |
| "image_end_token_id": -1, | |
| "intermediate_size": 8192, | |
| "num_hidden_layers": 48, | |
| "num_attention_heads": 16, | |
| "mm_projector_id": "patch_merge", | |
| "spatial_merge_size": 2, | |
| "hidden_size": 1664, | |
| "num_channels": 3, | |
| "image_size": 1540, | |
| "max_image_size": 1540, | |
| "patch_size": 14, | |
| "rope_theta": 10000.0, | |
| "add_pre_mm_projector_layer_norm": true, | |
| "adapter_bias": false | |
| } | |
| } |