Downloads · 30 days
139
2% of all-time downloads
LibraxisAI/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp4
Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp4 is a image-text-to-text model from LibraxisAI. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp4 is an mlx-vlm checkpoint derived from huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated, packaged for local multimodal experimentation on Apple…
Downloads · 30 days
139
2% of all-time downloads
All-time downloads
6.4K
Public
Parameters
35.1B
19.3 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors19.3 GB · 100%
How the weights are stored.
U3234.7B · 99%
From the Hugging Face model README
Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp4 is an mlx-vlm checkpoint derived from huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated, packaged for local multimodal experimentation on Apple Silicon.
Inference for this checkpoint has been tested with
LibraxisAI/mlx-batch-server.
This is the recommended tested path for operator-controlled local multimodal mlx-lm / mlx-vlm 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.
| Parameter | Value |
|---|---|
| Repository | LibraxisAI/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-vmlx-mxfp4 |
| Base model | huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated |
| Task | image-text-to-text |
| Library | mlx |
| Format | MLX / VMLX checkpoint |
| Quantization | MXFP4 |
| Target platform | Apple Silicon |
This card reports metadata present in the Hugging Face repository, existing frontmatter, or public config files. Missing benchmark, dataset, or training-run details are left explicit rather than reconstructed.
Use the library instructions above, or run this checkpoint through the tested local serving path: LibraxisAI/mlx-batch-server
End-to-end pipeline test 2026-04-22 on M3 Ultra (load → text → vision → unload), served via mlx-batch-server:
| Probe | TTFT | Output chars | Notes |
|---|---|---|---|
| Cold load | — | — | 21 s from cold to ready |
| Text — simple greeting (PL) | 0.51 s | 601 | Clean output, abliterated behaviour |
| Text — canonical (PL, literary) | 0.29 s | 718 | Concise reasoning trace |
| Vision — JPEG (Monument Valley) | 6.50 s | 873 | Accurate scene description |
3/3 probes passed. has_reasoning=True on all probes — this model emits reasoning traces via <think> markers.
apache-2.0. Check the upstream/base model license as well when a base model is declared.
𝚅𝚒𝚋𝚎𝚌𝚛𝚊𝚏𝚝𝚎𝚍. with AI Agents by VetCoders (c)2024-2026 LibraxisAI