Downloads · 30 days
56
7% of all-time downloads
Shiftedx/ornith-1.5-35b-a3b-affine4-router8-bf16recurrence-vision-mtplx
ornith-1.5-35b-a3b-affine4-router8-bf16recurrence-vision-mtplx is a image-text-to-text model from Shiftedx. 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 mit.
Affine 4-bit language body with 8-bit MoE router gates and recurrent-state inputs retained in BF16, plus BF16 vision and native BF16 MTP. Built from ornith-ai/Ornith-1.5-35B-A3B revision fbb995a for Apple Silicon.
Downloads · 30 days
56
7% of all-time downloads
All-time downloads
778
Public
Parameters
35.1B
24.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors24.3 GB · 100%
How the weights are stored.
U3234.7B · 99%
From the Hugging Face model README
Affine 4-bit language body with 8-bit MoE router gates and recurrent-state inputs retained in BF16, plus BF16 vision and native BF16 MTP. Built from ornith-ai/Ornith-1.5-35B-A3B revision fbb995a for Apple Silicon.
mtp/weights.safetensorsThe fail-closed precision recipe and conversion assertions are included in BUILD_RECIPE.json and conversion_receipt.json.
The matched AR/D1/D2/D3 sweep selected D1 at 118.50 decode tok/s on the qualification host.
mtplx serve \
--model Shiftedx/ornith-1.5-35b-a3b-affine4-router8-bf16recurrence-vision-mtplx \
--profile turbo \
--generation-mode mtp \
--load-mtp \
--depth 1
python -m mlx_vlm.generate \
--model Shiftedx/ornith-1.5-35b-a3b-affine4-router8-bf16recurrence-vision-mtplx \
--image image.jpg \
--prompt "Describe this image." \
--max-tokens 256
This table was generated from the frozen lightweight quant gate after the model weights were published. Categories remain separate; the benchmark does not produce a composite intelligence score.
| Lane | Passed | Accuracy | Mean wall time | Mean decode | Peak active memory |
|---|---|---|---|---|---|
| Quality | 6/10 | 60.0% | 7.60 s | 126.10 tok/s | 25.39 GiB |
| Long context | 11/15 | 73.3% | 37.04 s | 105.99 tok/s | 36.42 GiB |
| Tool calling | 6/6 | 100.0% | 1.54 s | 96.90 tok/s | 26.62 GiB |
| Agentic | 1/2 | 50.0% | 5.37 s | — tok/s | — |
| Vision | 2/4 | 50.0% | 1.35 s | 123.72 tok/s | 28.54 GiB |
bbaff3c9946d1c2fcd30f88138cf8db2970629f1off; MTP depth 1Scores are specific to the linked model revision, benchmark revision, runtime contract, and host. Changing weight precision, KV-cache precision, reasoning mode, template, or speculative depth creates a different benchmark candidate.
<!-- shiftedx-bench:end -->