Ornith-1.5-35B needs about 22.1 GB of memory at Q4_K_S (a 20.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 9 quants, from 12.3 GB (Q2_K_XL) to 38.5 GB (Q8_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Ornith-1.5-35B-A3B, a 36B mixture‑of‑experts LLM with 3B active parameters per token
Ornith-1.5-35B-A3B is a 36‑billion‑parameter model built on the qwen35moe architecture. It activates only about 3 billion parameters per token, enabling efficient inference while maintaining strong performance on coding and agentic tasks. The model is released under the MIT license.
Good at
- Strong coding and agentic benchmarks
- Efficient inference with MoE activation
- Large context support up to 262 144 tokens
Limits
- Requires 8 k context for memory estimates
- No vision or multimodal capabilities
- Mixture‑of‑experts may need more VRAM than dense models
Best for
- Coding assistants needing high accuracy
- Agentic workflows with tool use
- Long‑form text generation with extended context
Who it’s for. Developers and researchers building AI agents or coding assistants who need a large‑scale model with efficient MoE activation. The MIT license allows free use in commercial and non‑commercial projects.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K_XL | 12.3 GB | 13.5 GB | Too big | Get file → | |
| IQ3_XXS | 13.2 GB | 14.4 GB | Too big | Get file → | |
| Q3_K_XL | 16.8 GB | 18.0 GB | Too big | Get file → | |
| IQ4_XS | 17.7 GB | 18.9 GB | Too big | Get file → | |
| Q4_K_S | 20.9 GB | 22.1 GB | Too big | Get file → | |
| Q4_K_XL | 22.4 GB | 23.5 GB | Too big | Get file → | |
| Q5_K_XL | 26.6 GB | 27.8 GB | Too big | Get file → | |
| Q6_K_XL | 31.8 GB | 33.0 GB | Too big | Get file → | |
| Q8_K_XL | 38.5 GB | 39.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K_XL (12.29 GB file, ~13.5 GB VRAM). With 12 GB VRAM, Q3_K_XL (16.85 GB file, ~18 GB VRAM) is suitable. For 16 GB VRAM, Q4_K_XL (22.36 GB file, ~23.5 GB VRAM) offers a good balance of size and quality. Memory estimates are approximate.
What GPU do you need for Ornith-1.5-35B?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is IQ3_XXS (13.2 GB file, about 14.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_XL (22.4 GB file, about 23.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_XL (26.6 GB file, about 27.8 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_K_XL (38.5 GB file, about 39.6 GB in use).
Which Ornith-1.5-35B quant should you choose?
Q4_K_S (20.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is Q2_K_XL at 12.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ornith-1.5-35B
How much VRAM does Ornith-1.5-35B need?
About 22.1 GB at Q4_K_S with an 8K context window. That is the 20.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Ornith-1.5-35B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ornith-1.5-35B GGUF?
It depends on the quant: Q2_K_XL is 12.3 GB, IQ3_XXS is 13.2 GB, Q3_K_XL is 16.8 GB, IQ4_XS is 17.7 GB, Q4_K_S is 20.9 GB, Q4_K_XL is 22.4 GB and 3 more.
What context length does Ornith-1.5-35B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.
Where can I download Ornith-1.5-35B GGUF?
The files are on Hugging Face in the peculiar-ragdoll/Unsloth-Ornith-1.5-35B-A3B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Ornith-1.5-35B use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Ornith-1.5-35B-A3B on 8 GB VRAM?
Yes, using the Q2_K_XL quantized file (~13.5 GB VRAM estimate).
Does the model support vision or multimodal inputs?
No, the model is purely text‑only and does not include vision capabilities.
What is the context length I can use?
The model supports up to 262,144 tokens of context.