Qwen3.5-VL-122B-A10B-mlx-crk-mxfp4

Qwen3.5-VL-122B-A10B-mlx-crk-mxfp4 is an MLX vision-language checkpoint derived from Qwen/Qwen3.5-122B-A10B, packaged for local multimodal prompting on Apple Silicon.

Intended use

• Local image-and-text reasoning on Apple Silicon
• Document, screenshot, chart, and visual question answering experiments
• Operator-controlled multimodal prototyping where hosted inference is not desired

Out of scope

• Safety-critical decisions without domain expert review
• Claims of benchmark superiority not backed by published evaluation data
• Non-MLX runtime guarantees; this card documents the shipped HF checkpoint, not every possible serving stack
• High-stakes visual interpretation without human review

Training and conversion metadata

Parameter	Value
Repository	LibraxisAI/Qwen3.5-VL-122B-A10B-mlx-crk-mxfp4
Base model	Qwen/Qwen3.5-122B-A10B, dealignai/Qwen3.5-VL-122B-A10B-8bit-MLX-CRACK
Task	image-text-to-text
Library	mlx-vlm
Format	MLX / Apple Silicon checkpoint
Quantization	MXFP4
Architecture	Qwen3_5MoeForConditionalGeneration
Model files	13
Config model_type	qwen3_5_moe

This card only reports metadata present in the Hugging Face repository, existing card frontmatter, or public config files. Missing benchmark, dataset, or training-run details are left explicit rather than reconstructed.

Tested inference path

**Inference for this checkpoint has been tested with LibraxisAI/mlx-batch-server.**
This is the recommended tested path for operator-controlled local inference on Apple Silicon.

Aspect	Status
Tested runtime	LibraxisAI/mlx-batch-server
Target hardware	Apple Silicon
Inference mode	Local / self-hosted
Hugging Face Hosted Inference	Disabled for this repository (inference: false)

This does not claim compatibility with every possible serving stack. It documents the path that has been exercised for this published checkpoint.

Usage

CLI

pip install mlx-vlm

python -m mlx_vlm.generate \
  --model LibraxisAI/Qwen3.5-VL-122B-A10B-mlx-crk-mxfp4 \
  --image image.jpg \
  --prompt "Summarize the key signals in this document and list the next action items." \
  --max-tokens 256

Python

from mlx_vlm import generate, load

model, processor = load("LibraxisAI/Qwen3.5-VL-122B-A10B-mlx-crk-mxfp4")
response = generate(
    model,
    processor,
    prompt="Summarize the key signals in this document and list the next action items.",
    image="image.jpg",
    max_tokens=256,
)
print(response)

Example output

No public sample output is currently declared for this checkpoint.

Quantization notes

Aspect	Original/base checkpoint	This checkpoint
Lineage	Qwen/Qwen3.5-122B-A10B, dealignai/Qwen3.5-VL-122B-A10B-8bit-MLX-CRACK	LibraxisAI/Qwen3.5-VL-122B-A10B-mlx-crk-mxfp4
Runtime target	Upstream runtime format	MLX on Apple Silicon
Quantization	Base precision or upstream-declared format	MXFP4
Published quality delta	Not declared in public metadata	Not declared in public metadata

Limitations

• No public benchmarks for this checkpoint are declared in the model metadata.
• No public benchmark claims are made by this card unless listed in the frontmatter.
• Validate outputs on your own domain data before relying on this checkpoint.
• Memory use and speed depend heavily on the exact Apple Silicon generation, unified-memory size, and prompt length.

License

apache-2.0. Check the upstream/base model license as well when a base model is declared.

Citation

@misc{libraxisai-qwen3-5-vl-122b-a10b-mlx-crk-mxfp4,
  title = {Qwen3.5-VL-122B-A10B-mlx-crk-mxfp4},
  author = {LibraxisAI},
  year = {2026},
  howpublished = {\url{https://huggingface.co/LibraxisAI/Qwen3.5-VL-122B-A10B-mlx-crk-mxfp4}},
  note = {MLX checkpoint published by LibraxisAI}
}

---

𝚅𝚒𝚋𝚎𝚌𝚛𝚊𝚏𝚝𝚎𝚍. with AI Agents by VetCoders (c)2024-2026 LibraxisAI