Ornith 1.0 397B needs about 246.5 GB of memory at Q4_K_M (a 245.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 23 quants, from 112.7 GB (IQ1_S) to 793.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.0 GB.
Ornith 1.0 397B – a large‑scale, mixture‑of‑experts model for coding tasks
Ornith 1.0 397B is a 397‑billion‑parameter, Qwen3.5‑MoE model. It is trained on a 262144‑token context window and licensed under MIT. The model is optimized for efficient single‑GPU deployment with a variety of GGUF quantizations.
Good at
- Agentic coding
- Large context reasoning
- High‑quality code generation
Limits
- Requires large VRAM for full precision
- No vision support
- Mixture‑of‑experts may increase latency
Best for
- Coding interview preparation
- Automated code review
- Complex algorithm design
Who it’s for. Developers and researchers needing a powerful, open‑source coding assistant. The model is suitable for teams that can allocate sufficient GPU memory and prefer a permissive MIT license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 112.7 GB (4 parts) | 114.2 GB | Too big | Get file → | |
| IQ1_M | 118.9 GB (4 parts) | 120.4 GB | Too big | Get file → | |
| IQ2_XXS | 124.2 GB (4 parts) | 125.7 GB | Too big | Get file → | |
| IQ2_M | 124.4 GB (4 parts) | 125.9 GB | Too big | Get file → | |
| Q2_K_XL | 132.6 GB (4 parts) | 134.1 GB | Too big | Get file → | |
| IQ3_XXS | 147.6 GB (4 parts) | 149.1 GB | Too big | Get file → | |
| IQ3_S | 161.9 GB (5 parts) | 163.4 GB | Too big | Get file → | |
| Q3_K_M | 180.0 GB (5 parts) | 181.5 GB | Too big | Get file → | |
| Q3_K_XL | 180.2 GB (5 parts) | 181.7 GB | Too big | Get file → | |
| IQ4_XS | 192.1 GB (5 parts) | 193.6 GB | Too big | Get file → | |
| IQ4_NL | 196.1 GB (5 parts) | 197.6 GB | Too big | Get file → | |
| Q4_K_S | 229.7 GB (6 parts) | 231.2 GB | Too big | Get file → | |
| MXFP4_MOE | 237.9 GB (6 parts) | 239.4 GB | Too big | Get file → | |
| Q4_K_M | 245.0 GB (6 parts) | 246.5 GB | Too big | Get file → | |
| Q4_K_XL | 245.8 GB (6 parts) | 247.3 GB | Too big | Get file → | |
| Q5_K_S | 277.5 GB (7 parts) | 279.0 GB | Too big | Get file → | |
| Q5_K_M | 295.3 GB (8 parts) | 296.8 GB | Too big | Get file → | |
| Q5_K_XL | 295.9 GB (8 parts) | 297.4 GB | Too big | Get file → | |
| Q6_K | 329.5 GB (8 parts) | 331.0 GB | Too big | Get file → | |
| Q6_K_XL | 360.2 GB (9 parts) | 361.7 GB | Too big | Get file → | |
| Q8_0 | 421.5 GB (10 parts) | 423.0 GB | Too big | Get file → | |
| Q8_K_XL | 431.8 GB (10 parts) | 433.3 GB | Too big | Get file → | |
| BF16 | 793.0 GB (17 parts) | 794.5 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (112.69 GB file, 114.2 GB memory at 8k context). For 16 GB VRAM, IQ2_M (118.93 GB file, 120.4 GB memory) or Q2_K_XL (132.56 GB file, 134.1 GB memory). For 24 GB VRAM, Q4_K_M (245.02 GB file, 246.5 GB memory) or Q5_K_M (295.29 GB file, 296.8 GB memory).
What GPU do you need for Ornith 1.0 397B?
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: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Ornith 1.0 397B quant should you choose?
Q4_K_M is the usual starting point for Ornith 1.0 397B: it balances file size and quality well. Here it is a 245.0 GB file.
The Q8_0 file is 421.5 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ1_S at 112.7 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 1.0 397B
How much VRAM does Ornith 1.0 397B need?
About 246.5 GB at Q4_K_M with an 8K context window. That is the 245.0 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 1.0 397B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 114.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ornith 1.0 397B GGUF?
It depends on the quant: IQ1_S is 112.7 GB, IQ1_M is 118.9 GB, IQ2_XXS is 124.2 GB, IQ2_M is 124.4 GB, Q2_K_XL is 132.6 GB, IQ3_XXS is 147.6 GB and 17 more.
What context length does Ornith 1.0 397B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.0 GB at 8K and 4.0 GB at 32K.
Where can I download Ornith 1.0 397B GGUF?
The files are on Hugging Face in the unsloth/Ornith-1.0-397B-GGUF 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 1.0 397B 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 1.0 397B on a single 8 GB GPU?
The smallest quant, IQ1_S, requires about 114.2 GB of VRAM at 8k context, so an 8 GB GPU is insufficient.
What is the maximum context length supported?
The model was trained with a 262144‑token context window.
Is the model licensed for commercial use?
Yes, it is MIT licensed, allowing commercial deployment.