Ornith 1.5 35B A3B Abliterated needs about 22.3 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 21.2 GB (Q4_K_M) to 69.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Ornith 1.5 35B A3B Abliterated – a 35B mixture‑of‑experts model with vision support
Ornith 1.5 35B A3B Abliterated is a 35 billion‑parameter mixture‑of‑experts model based on the qwen35moe architecture. It activates only ~3 billion parameters per token and includes vision capabilities. The model is released under the MIT license.
Good at
- Strong coding and agentic benchmarks
- Vision inference with Q4_K_M
- Large context handling up to 262,144 tokens
Limits
- Requires 8 GB+ VRAM for Q4_K_M
- No native MTP speculative‑decoding head
- Abliteration may increase harmful content risk
Best for
- Local coding assistants
- Vision‑enabled inference on moderate GPUs
- Research on refusal‑direction editing
Who it’s for. Developers and researchers who need a large, vision‑capable model for local deployment and who are comfortable handling the safety implications of an abliterated checkpoint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 21.2 GB | 22.3 GB | Too big | Get file → | |
| Q8_0 | 36.9 GB | 38.1 GB | Too big | Get file → | |
| BF16 | 69.4 GB | 70.5 GB | Too big | Get file → |
For 8 GB VRAM, use the Q4_K_M quant (21.17 GB file, ~22.3 GB RAM at 8 k context). If more VRAM is available, Q8_0 (36.9 GB file, ~38.1 GB RAM) offers higher precision. BF16 provides the best quality but needs ~70 GB RAM.
What GPU do you need for Ornith 1.5 35B A3B Abliterated?
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: the best quant that fits is Q4_K_M (21.2 GB file, about 22.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (21.2 GB file, about 22.3 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (36.9 GB file, about 38.1 GB in use).
Which Ornith 1.5 35B A3B Abliterated quant should you choose?
Q4_K_M is the usual starting point for Ornith 1.5 35B A3B Abliterated: it balances file size and quality well. Here it is a 21.2 GB file.
The Q8_0 file is 36.9 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ornith 1.5 35B A3B Abliterated
How much VRAM does Ornith 1.5 35B A3B Abliterated need?
About 22.3 GB at Q4_K_M with an 8K context window. That is the 21.2 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 A3B Abliterated on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 22.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ornith 1.5 35B A3B Abliterated GGUF?
It depends on the quant: Q4_K_M is 21.2 GB, Q8_0 is 36.9 GB, BF16 is 69.4 GB.
What context length does Ornith 1.5 35B A3B Abliterated 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 A3B Abliterated GGUF?
The files are on Hugging Face in the PocketAiHub/Ornith-1.5-35B-A3B-Abliterated-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 1.5 35B A3B Abliterated 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 this model on 8 GB VRAM?
Yes, the Q4_K_M quant requires about 22.3 GB of RAM at 8 k context, which fits within 8 GB VRAM on a recent GPU with efficient memory management.
Does the model support vision?
Yes, the model includes vision support and the Q4_K_M quant passed an end‑to‑end image smoke test.
What are the safety implications of the abliterated version?
The abliterated checkpoint suppresses refusal behavior and may produce more harmful content; it should be evaluated and constrained for your use case.