malhajar Llama 2 13b chat tr needs about 3.5 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 19 quants, from 1.9 GB (Q5_K) to 13.8 GB (Q8_0).
malhajar Llama 2 13b chat tr is a 13B-parameter Llama model in GGUF format, quantized by RichardErkhov. Its trained context length is 4K tokens. The repository has 19 quant files, from 1.9 GB (Q5_K) to 13.8 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K | 1.9 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_M | 2.7 GB | 3.4 GB | Fits | Get file → | |
| Q5_K_S | 2.8 GB | 3.5 GB | Fits | Get file → | |
| Q2_K | 4.9 GB | 5.6 GB | Fits | Get file → | |
| Q5_K_M | 5.5 GB | 6.3 GB | Fits | Get file → | |
| Q3_K_S | 5.7 GB | 6.5 GB | Fits | Get file → | |
| Q4_1 | 5.8 GB | 6.7 GB | Fits | Get file → | |
| Q4_K_S | 6.0 GB | 6.8 GB | Fits | Get file → | |
| Q3_K | 6.3 GB | 7.2 GB | Tight | Get file → | |
| Q3_K_M | 6.3 GB | 7.2 GB | Tight | Get file → | |
| Q3_K_L | 6.9 GB | 7.8 GB | Tight | Get file → | |
| IQ4_XS | 7.0 GB | 7.9 GB | Tight | Get file → | |
| Q4_0 | 7.4 GB | 8.3 GB | Too big | Get file → | |
| IQ4_NL | 7.4 GB | 8.4 GB | Too big | Get file → | |
| Q4_K | 7.9 GB | 8.8 GB | Too big | Get file → | |
| Q5_0 | 9.0 GB | 10.0 GB | Too big | Get file → | |
| Q5_1 | 9.5 GB | 10.6 GB | Too big | Get file → | |
| Q6_K | 10.7 GB | 11.8 GB | Too big | Get file → | |
| Q8_0 | 13.8 GB | 15.2 GB | Too big | Get file → |
What GPU do you need for malhajar Llama 2 13b chat tr?
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 Q5_K_S (2.8 GB file, about 3.6 GB in use).
- 6 GB VRAM: the best quant that fits is Q2_K (4.9 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q3_K (6.3 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_1 (9.5 GB file, about 11.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 16.0 GB in use).
Which malhajar Llama 2 13b chat tr quant should you choose?
Q4_K_M is the usual starting point for malhajar Llama 2 13b chat tr: it balances file size and quality well. Here it is a 2.7 GB file.
The Q8_0 file is 13.8 GB, about 5.1 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.
If memory is tight, the smallest file is Q5_K at 1.9 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about malhajar Llama 2 13b chat tr
How much VRAM does malhajar Llama 2 13b chat tr need?
About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.7 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 malhajar Llama 2 13b chat tr on an 8 GB GPU?
Yes, with Q3_K: the 6.3 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of malhajar Llama 2 13b chat tr GGUF?
It depends on the quant: Q5_K is 1.9 GB, Q4_K_M is 2.7 GB, Q5_K_S is 2.8 GB, Q2_K is 4.9 GB, Q5_K_M is 5.5 GB, Q3_K_S is 5.7 GB and 13 more.
What context length does malhajar Llama 2 13b chat tr support?
The GGUF header lists a trained context length of 4,096 tokens (4K).
Where can I download malhajar Llama 2 13b chat tr GGUF?
The files are on Hugging Face in the RichardErkhov/malhajar_-_Llama-2-13b-chat-tr-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.