LL

laislemke LLaMA 2 vicuna 7b slerp

LlamaGGUF by RichardErkhovUpdated 2024-08-06
Download on Hugging Face
Parameters6.74B
Context32K
Layers—
Architecturellama
Smallest quant0.1 GB
Quick answer

laislemke LLaMA 2 vicuna 7b slerp needs about 1.1 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 0.1 GB (IQ4_NL) to 4.7 GB (Q5_0).

laislemke LLaMA 2 vicuna 7b slerp is a 6.74B-parameter Llama model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 22 quant files, from 0.1 GB (IQ4_NL) to 4.7 GB (Q5_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_NL0.1 GB 0.6 GB
Fits Get file →
Q8_00.2 GB 0.7 GB
Fits Get file →
Q6_K0.3 GB 0.8 GB
Fits Get file →
Q4_00.3 GB 0.8 GB
Fits Get file →
Q4_K0.3 GB 0.8 GB
Fits Get file →
Q5_10.4 GB 0.9 GB
Fits Get file →
IQ4_XS0.4 GB 1.0 GB
Fits Get file →
Q4_K_M0.6 GB 1.1 GB
Fits Get file →
Q5_K_M0.6 GB 1.2 GB
Fits Get file →
Q3_K0.7 GB 1.2 GB
Fits Get file →
IQ3_S0.8 GB 1.4 GB
Fits Get file →
Q4_K_S0.9 GB 1.6 GB
Fits Get file →
IQ3_XS1.2 GB 1.9 GB
Fits Get file →
Q5_K2.4 GB 3.2 GB
Fits Get file →
Q2_K2.5 GB 3.3 GB
Fits Get file →
Q3_K_S2.9 GB 3.8 GB
Fits Get file →
IQ3_M3.1 GB 4.0 GB
Fits Get file →
Q3_K_M3.3 GB 4.2 GB
Fits Get file →
Q5_K_S3.5 GB 4.5 GB
Fits Get file →
Q3_K_L3.6 GB 4.5 GB
Fits Get file →
Q4_14.2 GB 5.2 GB
Fits Get file →
Q5_04.7 GB 5.7 GB
Fits Get file →

What GPU do you need for laislemke LLaMA 2 vicuna 7b slerp?

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_M (3.1 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q5_0 (4.7 GB file, about 5.7 GB in use).

Which laislemke LLaMA 2 vicuna 7b slerp quant should you choose?

Q4_K_M is the usual starting point for laislemke LLaMA 2 vicuna 7b slerp: it balances file size and quality well. Here it is a 0.6 GB file.

The Q8_0 file is 0.2 GB, about 0.4 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.

If memory is tight, the smallest file is IQ4_NL at 0.1 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.74B
Trained context32,768 tokens

Source

Quantized byRichardErkhov
FamilyLlama
Downloads (HF)684
Last updated2024-08-06

Frequently asked questions about laislemke LLaMA 2 vicuna 7b slerp

How much VRAM does laislemke LLaMA 2 vicuna 7b slerp need?

About 1.1 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 laislemke LLaMA 2 vicuna 7b slerp on an 8 GB GPU?

Yes, with Q5_0: the 4.7 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of laislemke LLaMA 2 vicuna 7b slerp GGUF?

It depends on the quant: IQ4_NL is 0.1 GB, Q8_0 is 0.2 GB, Q6_K is 0.3 GB, Q4_0 is 0.3 GB, Q4_K is 0.3 GB, Q5_1 is 0.4 GB and 16 more.

What context length does laislemke LLaMA 2 vicuna 7b slerp support?

The GGUF header lists a trained context length of 32,768 tokens (32K).

Where can I download laislemke LLaMA 2 vicuna 7b slerp GGUF?

The files are on Hugging Face in the RichardErkhov/laislemke_-_LLaMA-2-vicuna-7b-slerp-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Llama models

All Llama →

Other small models

All small models →