Oasst Sft 4 Pythia 12b Epoch 3.5 needs about 16.3 GB of memory at Q6_K (a 9.7 GB file) with an 8K context window, so it fits on a 24 GB GPU.
Oasst Sft 4 Pythia 12b Epoch 3.5 is a 11.8B-parameter Oasst model in GGUF format, quantized by ArtyomSubDiv. Its trained context length is 2K tokens. The repository has 1 quant file, from 9.7 GB (Q6_K) to 9.7 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 9.7 GB | 11.7 GB | Too big | Get file → |
What GPU do you need for Oasst Sft 4 Pythia 12b Epoch 3.5?
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 Q6_K (9.7 GB file, about 16.3 GB in use).
Which Oasst Sft 4 Pythia 12b Epoch 3.5 quant should you choose?
Q6_K (9.7 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Oasst Sft 4 Pythia 12b Epoch 3.5
How much VRAM does Oasst Sft 4 Pythia 12b Epoch 3.5 need?
About 16.3 GB at Q6_K with an 8K context window. That is the 9.7 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 Oasst Sft 4 Pythia 12b Epoch 3.5 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Oasst Sft 4 Pythia 12b Epoch 3.5 GGUF?
It depends on the quant: Q6_K is 9.7 GB.
What context length does Oasst Sft 4 Pythia 12b Epoch 3.5 support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 6.0 GB at 8K and 1.5 GB at 2K.
Where can I download Oasst Sft 4 Pythia 12b Epoch 3.5 GGUF?
The files are on Hugging Face in the ArtyomSubDiv/oasst-sft-4-pythia-12b-epoch-3.5-Q6_K-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 Oasst Sft 4 Pythia 12b Epoch 3.5 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.