cstr llama3 8b spaetzle v33 needs about 4.1 GB of memory at Q2_K (a 3.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 2.0 GB (Q3_K_S) to 3.7 GB (IQ3_S).
cstr llama3 8b spaetzle v33 is a 8.03B-parameter Llama model in GGUF format, quantized by RichardErkhov. Its trained context length is 8K tokens. The repository has 4 quant files, from 2.0 GB (Q3_K_S) to 3.7 GB (IQ3_S).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 2.0 GB | 2.7 GB | Fits | Get file → | |
| Q2_K | 3.2 GB | 4.1 GB | Fits | Get file → | |
| IQ3_XS | 3.5 GB | 4.4 GB | Fits | Get file → | |
| IQ3_S | 3.7 GB | 4.6 GB | Fits | Get file → |
What GPU do you need for cstr llama3 8b spaetzle v33?
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 Q3_K_S (2.0 GB file, about 2.7 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_S (3.7 GB file, about 4.6 GB in use).
Which cstr llama3 8b spaetzle v33 quant should you choose?
Q2_K (3.2 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
If memory is tight, the smallest file is Q3_K_S at 2.0 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
Frequently asked questions about cstr llama3 8b spaetzle v33
How much VRAM does cstr llama3 8b spaetzle v33 need?
About 4.1 GB at Q2_K with an 8K context window. That is the 3.2 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 cstr llama3 8b spaetzle v33 on an 8 GB GPU?
Yes, with IQ3_S: the 3.7 GB file needs about 4.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of cstr llama3 8b spaetzle v33 GGUF?
It depends on the quant: Q3_K_S is 2.0 GB, Q2_K is 3.2 GB, IQ3_XS is 3.5 GB, IQ3_S is 3.7 GB.
What context length does cstr llama3 8b spaetzle v33 support?
The GGUF header lists a trained context length of 8,192 tokens (8K).
Where can I download cstr llama3 8b spaetzle v33 GGUF?
The files are on Hugging Face in the RichardErkhov/cstr_-_llama3-8b-spaetzle-v33-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.