llama 3 70B Instruct abliterated CQ needs about 36.4 GB of memory at Q3_K (a 33.2 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 4 quants, from 32.7 GB to 35.3 GB.
llama 3 70B Instruct abliterated CQ is a 70.6B-parameter Llama model in GGUF format, quantized by NexesQuants. Its trained context length is 8K tokens. The repository has 4 quant files, from 32.7 GB to 35.3 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 32.7 GB | 35.9 GB | Too big | Get file → | |
| Q3_K | 33.2 GB | 36.4 GB | Too big | Get file → | |
| — | 33.6 GB | 36.8 GB | Too big | Get file → | |
| — | 35.3 GB | 38.4 GB | Too big | Get file → |
What GPU do you need for llama 3 70B Instruct abliterated CQ?
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 the main file (35.3 GB file, about 38.4 GB in use).
Which llama 3 70B Instruct abliterated CQ quant should you choose?
Q3_K (33.2 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is the first one in the table at 32.7 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about llama 3 70B Instruct abliterated CQ
How much VRAM does llama 3 70B Instruct abliterated CQ need?
About 36.4 GB at Q3_K with an 8K context window. That is the 33.2 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 llama 3 70B Instruct abliterated CQ on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 35.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of llama 3 70B Instruct abliterated CQ GGUF?
It depends on the quant: file is 32.7 GB, Q3_K is 33.2 GB, file is 33.6 GB, file is 35.3 GB.
What context length does llama 3 70B Instruct abliterated CQ 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 llama 3 70B Instruct abliterated CQ GGUF?
The files are on Hugging Face in the NexesQuants/llama-3-70B-Instruct-abliterated-CQ-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.