llama 3.1 thinker 8b instruct needs about 17.6 GB of memory at F16 (a 16.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 6.6 GB (Q6_K) to 32.1 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
llama 3.1 thinker 8b instruct is a 8.03B-parameter Llama model in GGUF format, quantized by Anoxiom. Its trained context length is 128K tokens. The repository has 3 quant files, from 6.6 GB (Q6_K) to 32.1 GB (F32).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 6.6 GB | 8.2 GB | Too big | Get file → | |
| F16 | 16.1 GB | 17.6 GB | Too big | Get file → | |
| F32 | 32.1 GB | 33.7 GB | Too big | Get file → |
What GPU do you need for llama 3.1 thinker 8b instruct?
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: the best quant that fits is Q6_K (6.6 GB file, about 8.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 8.2 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 17.6 GB in use).
- 32 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 17.6 GB in use).
- 48 GB VRAM: the best quant that fits is F32 (32.1 GB file, about 33.7 GB in use).
Which llama 3.1 thinker 8b instruct quant should you choose?
F16 (16.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is Q6_K at 6.6 GB, with the quality trade-offs that come with fewer bits. 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
Source
Frequently asked questions about llama 3.1 thinker 8b instruct
How much VRAM does llama 3.1 thinker 8b instruct need?
About 17.6 GB at F16 with an 8K context window. That is the 16.1 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 3.1 thinker 8b instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of llama 3.1 thinker 8b instruct GGUF?
It depends on the quant: Q6_K is 6.6 GB, F16 is 16.1 GB, F32 is 32.1 GB.
What context length does llama 3.1 thinker 8b instruct support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download llama 3.1 thinker 8b instruct GGUF?
The files are on Hugging Face in the Anoxiom/llama_3.1_thinker_8b_instruct repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does llama 3.1 thinker 8b instruct 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.