ByteShape Llama 3.1 8B Instruct needs about 4.2 GB of memory at IQ3_S (a 3.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 18 quants, from 2.6 GB (IQ3_S) to 4.3 GB (Q4_K_S).
ByteShape Llama 3.1 8B Instruct is a 8.03B-parameter Llama model in GGUF format, quantized by tiktemu. Its trained context length is 128K tokens. The repository has 18 quant files, from 2.6 GB (IQ3_S) to 4.3 GB (Q4_K_S).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_S | 2.6 GB | 3.4 GB | Fits | Get file → | |
| IQ3_S | 2.7 GB | 3.6 GB | Fits | Get file → | |
| IQ3_S | 2.9 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_S | 2.9 GB | 3.8 GB | Fits | Get file → | |
| IQ3_S | 3.0 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_S | 3.1 GB | 3.9 GB | Fits | Get file → | |
| IQ3_S | 3.1 GB | 4.0 GB | Fits | Get file → | |
| Q3_K_S | 3.3 GB | 4.1 GB | Fits | Get file → | |
| IQ3_S | 3.3 GB | 4.2 GB | Fits | Get file → | |
| Q3_K_S | 3.4 GB | 4.3 GB | Fits | Get file → | |
| Q3_K_S | 3.4 GB | 4.3 GB | Fits | Get file → | |
| IQ4_XS | 3.6 GB | 4.5 GB | Fits | Get file → | |
| Q4_K_S | 3.6 GB | 4.6 GB | Fits | Get file → | |
| Q4_K_S | 3.9 GB | 4.8 GB | Fits | Get file → | |
| IQ4_XS | 4.0 GB | 4.9 GB | Fits | Get file → | |
| IQ4_XS | 4.1 GB | 5.1 GB | Fits | Get file → | |
| Q4_K_S | 4.2 GB | 5.2 GB | Fits | Get file → | |
| Q4_K_S | 4.3 GB | 5.3 GB | Fits | Get file → |
What GPU do you need for ByteShape Llama 3.1 8B Instruct?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is IQ3_S (3.1 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K_S (4.3 GB file, about 5.3 GB in use).
Which ByteShape Llama 3.1 8B Instruct quant should you choose?
IQ3_S (3.3 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 IQ3_S at 2.6 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 ByteShape Llama 3.1 8B Instruct
How much VRAM does ByteShape Llama 3.1 8B Instruct need?
About 4.2 GB at IQ3_S with an 8K context window. That is the 3.3 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 ByteShape Llama 3.1 8B Instruct on an 8 GB GPU?
Yes, with Q4_K_S: the 4.3 GB file needs about 5.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of ByteShape Llama 3.1 8B Instruct GGUF?
It depends on the quant: IQ3_S is 2.6 GB, IQ3_S is 2.7 GB, IQ3_S is 2.9 GB, Q3_K_S is 2.9 GB, IQ3_S is 3.0 GB, Q3_K_S is 3.1 GB and 12 more.
What context length does ByteShape Llama 3.1 8B Instruct support?
The GGUF header lists a trained context length of 131,072 tokens (128K).
Where can I download ByteShape Llama 3.1 8B Instruct GGUF?
The files are on Hugging Face in the tiktemu/ByteShape___Llama-3.1-8B-Instruct-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 ByteShape Llama 3.1 8B Instruct use?
Hugging Face lists the license as llama3.1. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.