Ostrich 70B needs about 43.2 GB of memory at Q4_0 (a 40.0 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 6 quants, from 34.3 GB (Q3_K) to 75.0 GB (Q8_0).
Ostrich 70B – a 70‑billion‑parameter Llama model fine‑tuned on niche topics
Ostrich 70B is a 70‑billion‑parameter Llama model fine‑tuned from Llama3‑70B. It was trained on health, nutrition, libertarian and Nostr notes, and other niche content. The model is released under the Apache‑2.0 license and supports a 8192‑token context window.
Good at
- Niche topic discussion
- Health and nutrition queries
- Libertarian viewpoints
Limits
- Large memory requirement for 8k context
- No vision or multimodal support
- Potential for hallucinations
Best for
- Researching niche health topics
- Exploring libertarian perspectives
- Generating detailed policy discussions
Who it’s for. Users who need in‑depth answers on niche subjects such as health, nutrition, and libertarian topics. It is suitable for researchers and enthusiasts who can handle the model’s memory demands and are aware of its bias risks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K | 34.3 GB | 37.5 GB | Too big | Get file → | |
| Q4_0 | 40.0 GB | 43.2 GB | Too big | Get file → | |
| Q4_0 | 40.0 GB | 43.2 GB | Too big | Get file → | |
| Q4_0 | 40.0 GB | 43.2 GB | Too big | Get file → | |
| Q5_K | 49.9 GB | 53.1 GB | Too big | Get file → | |
| Q8_0 | 75.0 GB (2 parts) | 78.2 GB | Too big | Get file → |
For 8‑GB VRAM use Q3_K (34.27 GB file, ~37.5 GB memory). For 16‑GB VRAM use Q4_0 (39.97 GB file, ~43.2 GB memory). For 24‑GB VRAM use Q5_K (49.95 GB file, ~53.1 GB memory). The Q8_0 split requires 2 shards and ~78.2 GB memory at 8k context.
What GPU do you need for Ostrich 70B?
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: the best quant that fits is Q4_0 (40.0 GB file, about 43.2 GB in use).
Which Ostrich 70B quant should you choose?
Q4_0 (40.0 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 Q3_K at 34.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ostrich 70B
How much VRAM does Ostrich 70B need?
About 43.2 GB at Q4_0 with an 8K context window. That is the 40.0 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 Ostrich 70B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 37.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ostrich 70B GGUF?
It depends on the quant: Q3_K is 34.3 GB, Q4_0 is 40.0 GB, Q4_0 is 40.0 GB, Q4_0 is 40.0 GB, Q5_K is 49.9 GB, Q8_0 is 75.0 GB.
What context length does Ostrich 70B support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.7 GB at 8K and 2.7 GB at 8K.
Where can I download Ostrich 70B GGUF?
The files are on Hugging Face in the some1nostr/Ostrich-70B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Ostrich 70B use?
Hugging Face lists the license as apache-2.0. 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 Ostrich 70B on 8 GB VRAM?
No, the smallest quant requires ~37.5 GB memory at 8k context. 8 GB VRAM is insufficient.
Does Ostrich 70B support image input?
No, the model has no vision or multimodal capabilities.
What license applies to Ostrich 70B?
The model is released under the Apache‑2.0 license.