LL

oopere pruned llama 1b

LlamaGGUF by RichardErkhovUpdated 2024-10-31
Download on Hugging Face
Parameters1B
Context128K
Layers16
Architecturellama
Smallest quant0.2 GB
Quick answer

oopere pruned llama 1b needs about 1.8 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 19 quants, from 0.2 GB (Q4_0) to 1.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.1 GB.

oopere pruned llama 1b is a 1B-parameter Llama model in GGUF format, quantized by RichardErkhov. Its trained context length is 128K tokens. The repository has 19 quant files, from 0.2 GB (Q4_0) to 1.1 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.2 GB 1.0 GB
Fits Get file →
Q4_10.2 GB 1.0 GB
Fits Get file →
Q5_00.2 GB 1.0 GB
Fits Get file →
Q5_10.2 GB 1.0 GB
Fits Get file →
Q8_00.3 GB 1.1 GB
Fits Get file →
IQ4_NL0.3 GB 1.1 GB
Fits Get file →
Q2_K0.9 GB 1.6 GB
Fits Get file →
Q3_K_S0.9 GB 1.7 GB
Fits Get file →
Q3_K0.9 GB 1.7 GB
Fits Get file →
Q3_K_M0.9 GB 1.7 GB
Fits Get file →
Q3_K_L0.9 GB 1.7 GB
Fits Get file →
IQ4_XS1.0 GB 1.7 GB
Fits Get file →
Q4_K_S1.0 GB 1.8 GB
Fits Get file →
Q4_K1.0 GB 1.8 GB
Fits Get file →
Q4_K_M1.0 GB 1.8 GB
Fits Get file →
Q5_K_S1.1 GB 1.8 GB
Fits Get file →
Q5_K1.1 GB 1.8 GB
Fits Get file →
Q5_K_M1.1 GB 1.8 GB
Fits Get file →
Q6_K1.1 GB 1.9 GB
Fits Get file →

What GPU do you need for oopere pruned llama 1b?

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: the best quant that fits is Q6_K (1.1 GB file, about 1.9 GB in use).

Which oopere pruned llama 1b quant should you choose?

Q4_K_M is the usual starting point for oopere pruned llama 1b: it balances file size and quality well. Here it is a 1.0 GB file.

The Q8_0 file is 0.3 GB, about 0.3 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 Q4_0 at 0.2 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
Parameters1B
Layers16
Trained context131,072 tokens
KV cache (fp16)32 KB per token

Source

Quantized byRichardErkhov
FamilyLlama
Downloads (HF)25
Last updated2024-10-31

Frequently asked questions about oopere pruned llama 1b

How much VRAM does oopere pruned llama 1b need?

About 1.8 GB at Q4_K_M with an 8K context window. That is the 1.0 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 oopere pruned llama 1b on an 8 GB GPU?

Yes, with Q6_K: the 1.1 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of oopere pruned llama 1b GGUF?

It depends on the quant: Q4_0 is 0.2 GB, Q4_1 is 0.2 GB, Q5_0 is 0.2 GB, Q5_1 is 0.2 GB, Q8_0 is 0.3 GB, IQ4_NL is 0.3 GB and 13 more.

What context length does oopere pruned llama 1b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.1 GB at 32K.

Where can I download oopere pruned llama 1b GGUF?

The files are on Hugging Face in the RichardErkhov/oopere_-_pruned-llama-1b-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 tiny models

All tiny models →