4yo1 llama3 pre1 pre2 inst3 ds lora3 needs about 1.2 GB of memory at Q4_K_M (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 0.6 GB (Q4_K_M) to 8.3 GB (Q8_0).
4yo1 llama3 pre1 pre2 inst3 ds lora3 is a 8.2B-parameter Llama model in GGUF format, quantized by RichardErkhov. Its trained context length is 8K tokens. The repository has 22 quant files, from 0.6 GB (Q4_K_M) to 8.3 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q3_K_L | 1.4 GB | 2.1 GB | Fits | Get file → | |
| Q2_K | 3.3 GB | 4.2 GB | Fits | Get file → | |
| IQ3_XS | 3.6 GB | 4.6 GB | Fits | Get file → | |
| Q3_K_S | 3.8 GB | 4.7 GB | Fits | Get file → | |
| IQ3_S | 3.8 GB | 4.7 GB | Fits | Get file → | |
| IQ3_M | 3.9 GB | 4.9 GB | Fits | Get file → | |
| Q3_K | 4.1 GB | 5.1 GB | Fits | Get file → | |
| Q3_K_M | 4.1 GB | 5.1 GB | Fits | Get file → | |
| IQ4_XS | 4.6 GB | 5.7 GB | Fits | Get file → | |
| Q4_0 | 4.8 GB | 5.9 GB | Fits | Get file → | |
| Q4_K_S | 4.8 GB | 5.9 GB | Fits | Get file → | |
| IQ4_NL | 4.8 GB | 5.9 GB | Fits | Get file → | |
| Q4_K | 5.0 GB | 6.1 GB | Fits | Get file → | |
| Q4_1 | 5.3 GB | 6.4 GB | Fits | Get file → | |
| Q5_0 | 5.7 GB | 6.8 GB | Fits | Get file → | |
| Q5_K_S | 5.7 GB | 6.9 GB | Fits | Get file → | |
| Q5_K | 5.9 GB | 7.1 GB | Fits | Get file → | |
| Q5_K_M | 5.9 GB | 7.1 GB | Fits | Get file → | |
| Q5_1 | 6.2 GB | 7.5 GB | Tight | Get file → | |
| Q6_K | 6.7 GB | 8.0 GB | Too big | Get file → | |
| Q8_0 | 8.3 GB | 9.8 GB | Too big | Get file → |
What GPU do you need for 4yo1 llama3 pre1 pre2 inst3 ds lora3?
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_L (1.4 GB file, about 2.1 GB in use).
- 6 GB VRAM: the best quant that fits is IQ4_NL (4.8 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (6.7 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.3 GB file, about 9.8 GB in use).
Which 4yo1 llama3 pre1 pre2 inst3 ds lora3 quant should you choose?
Q4_K_M is the usual starting point for 4yo1 llama3 pre1 pre2 inst3 ds lora3: it balances file size and quality well. Here it is a 0.6 GB file.
The Q8_0 file is 8.3 GB, about 13.4 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about 4yo1 llama3 pre1 pre2 inst3 ds lora3
How much VRAM does 4yo1 llama3 pre1 pre2 inst3 ds lora3 need?
About 1.2 GB at Q4_K_M with an 8K context window. That is the 0.6 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 4yo1 llama3 pre1 pre2 inst3 ds lora3 on an 8 GB GPU?
Yes, with Q6_K: the 6.7 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of 4yo1 llama3 pre1 pre2 inst3 ds lora3 GGUF?
It depends on the quant: Q4_K_M is 0.6 GB, Q3_K_L is 1.4 GB, Q2_K is 3.3 GB, IQ3_XS is 3.6 GB, Q3_K_S is 3.8 GB, IQ3_S is 3.8 GB and 16 more.
What context length does 4yo1 llama3 pre1 pre2 inst3 ds lora3 support?
The GGUF header lists a trained context length of 8,192 tokens (8K).
Where can I download 4yo1 llama3 pre1 pre2 inst3 ds lora3 GGUF?
The files are on Hugging Face in the RichardErkhov/4yo1_-_llama3-pre1-pre2-inst3-ds-lora3-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.