Model library / ornith-ai
Ornith-1.5-35B-A3B is a 36-billion-parameter mixture-of-experts language model released by ornith-ai.
Mixture of experts, count not published
Context length in tokens, as published
Weights at the released precision
Licence declared on the repository
Overview
Ornith-1.5-35B-A3B is a mid-size mixture-of-experts model built on the Qwen3.5 architecture. The publisher describes it as part of a self-improvement loop that generates training tasks, constructs scaffolds and optimises solution rollouts, aiming to improve policy performance through reinforcement learning.
In practice the model contains 36 billion parameters but activates roughly 3 billion per token. It supports a context window of 262 144 tokens, is distributed under the MIT licence and uses bfloat16 weight format. These characteristics affect memory, latency and licensing considerations for deployment.
Specification
| Repository | ornith-ai/Ornith-1.5-35B-A3B |
| Publisher | ornith-ai |
| Published | 18 August 2026 |
| Architecture | Qwen3_5MoeForConditionalGeneration |
| Model type | qwen3_5_moe |
| Parameters | 35,951,822,704 |
| Layers | 40 |
| Hidden size | 2,048 |
| Attention heads | 16, 2 key/value heads |
| Context length | 262,144 tokens |
| Vocabulary | 248,320 tokens |
| Weight format | bfloat16 |
| Licence | mit |
Memory
Parameter count multiplied by the bytes each format uses. The key-value cache comes on top.
| Precision | Weights | Notes |
|---|---|---|
| bf16 | 67.0 GiB | Full precision as released |
| fp8 | 33.5 GiB | 8-bit, near-lossless on most models |
| int4 | 16.7 GiB | 4-bit, smallest footprint |
The cache costs 80 KiB per token at 16-bit, so the full 262,144-token context of one request needs about 20.0 GiB. Concurrency multiplies that number, not the weights.
Hardware
At the released precision, with 90% of the card given to the server and 2.5 GiB kept for the runtime. The context column is what is left for the cache on that setup.
| GPU | Cards needed | Free for cache | Context it holds |
|---|---|---|---|
| RTX 4090 24GB | 4 | 9.4 GiB | about 123,660 tokens |
| RTX 5090 32GB | 4 | 38.2 GiB | the full 262,144 tokens |
| L40S 48GB | 2 | 14.4 GiB | about 189,196 tokens |
| A100 80GB | 1 | 2.5 GiB | about 33,220 tokens |
| H100 80GB | 1 | 2.5 GiB | about 33,220 tokens |
| RTX PRO 6000 96GB | 1 | 16.9 GiB | about 221,964 tokens |
| H200 141GB | 1 | 57.4 GiB | the full 262,144 tokens |
Serving
A vLLM launch line for the shape above. Check the model card for a runtime the publisher recommends.
vllm serve ornith-ai/Ornith-1.5-35B-A3B \ --max-model-len 122880 \ --gpu-memory-utilization 0.90
Questions
The weights take about 67 GiB at the released precision. That fits on one A100 80GB, which leaves roughly 3 GiB for the key-value cache.
The repository declares mit. Read the licence text before commercial use: the name alone does not tell you what is allowed.
The configuration allows 262,144 tokens. Whether the whole window is usable depends on the memory left for the cache, which the hardware table works out per card.
This page is a reference, and Aiqre does not serve this model today. We deploy open-weight models on dedicated EU hardware on request, so if you want an OpenAI-compatible endpoint for it, email [email protected] with the model name and roughly what volume you expect.
Also in the library
Ornith-1.5-9B is a 9.7 billion-parameter dense model from ornith-ai that continues self-improvement through automated task genera…
Pantheon-Reasoning-26B-A4B-1.1-V2 is a 26.5 billion-parameter Gemma-4 mixture-of-experts finetune aimed at role-play scenarios, i…
Nex-N2.5-mini is a 35.1 billion-parameter mixture-of-experts language model released under Apache-2.0.
K2-Horizon-32B-Stage1 is a 32-billion-parameter dense decoder-only model released by IFM for benchmarking agentic, coding and rea…
Hosting
Tell us the model and roughly what volume you expect. We reply with a price and an OpenAI-compatible endpoint, with your prompts never stored.