LL

gradientai Gradient Llama 3.1 8B Instruct 1048k

LlamaGGUF by RichardErkhovUpdated 2024-08-03
Download on Hugging Face
Parameters2.7B
Context—
Layers—
Architecture—
Smallest quant0.0 GB
Quick answer

gradientai Gradient Llama 3.1 8B Instruct 1048k needs about 0.8 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 0.0 GB (Q4_K_S) to 6.6 GB (Q6_K).

gradientai Gradient Llama 3.1 8B Instruct 1048k is a 2.7B-parameter Llama model in GGUF format, quantized by RichardErkhov. The repository has 22 quant files, from 0.0 GB (Q4_K_S) to 6.6 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S0.0 GB 0.5 GB
Fits Get file →
Q3_K0.0 GB 0.5 GB
Fits Get file →
Q3_K_M0.0 GB 0.5 GB
Fits Get file →
IQ3_M0.0 GB 0.5 GB
Fits Get file →
IQ4_NL0.0 GB 0.5 GB
Fits Get file →
Q4_K_M0.2 GB 0.8 GB
Fits Get file →
Q4_00.3 GB 0.8 GB
Fits Get file →
IQ4_XS0.3 GB 0.8 GB
Fits Get file →
Q4_K0.3 GB 0.8 GB
Fits Get file →
IQ3_S0.4 GB 0.9 GB
Fits Get file →
Q3_K_S0.5 GB 1.1 GB
Fits Get file →
IQ3_XS1.1 GB 1.7 GB
Fits Get file →
Q5_K1.1 GB 1.8 GB
Fits Get file →
Q4_11.6 GB 2.3 GB
Fits Get file →
Q3_K_L2.0 GB 2.7 GB
Fits Get file →
Q5_K_M2.0 GB 2.7 GB
Fits Get file →
Q5_K_S2.3 GB 3.1 GB
Fits Get file →
Q2_K3.2 GB 4.1 GB
Fits Get file →
Q5_04.5 GB 5.6 GB
Fits Get file →
Q8_05.7 GB 6.9 GB
Fits Get file →
Q5_16.1 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 7.9 GB
Tight Get file →

What GPU do you need for gradientai Gradient Llama 3.1 8B Instruct 1048k?

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 (2.3 GB file, about 3.1 GB in use).
  • 6 GB VRAM: the best quant that fits is Q5_0 (4.5 GB file, about 5.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 7.9 GB in use).

Which gradientai Gradient Llama 3.1 8B Instruct 1048k quant should you choose?

Q4_K_M is the usual starting point for gradientai Gradient Llama 3.1 8B Instruct 1048k: it balances file size and quality well. Here it is a 0.2 GB file.

The Q8_0 file is 5.7 GB, about 24.3 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_K_S at 0.0 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

Parameters2.7B

Source

Quantized byRichardErkhov
FamilyLlama
Downloads (HF)57
Last updated2024-08-03

Frequently asked questions about gradientai Gradient Llama 3.1 8B Instruct 1048k

How much VRAM does gradientai Gradient Llama 3.1 8B Instruct 1048k need?

About 0.8 GB at Q4_K_M with an 8K context window. That is the 0.2 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 gradientai Gradient Llama 3.1 8B Instruct 1048k on an 8 GB GPU?

Yes, with Q6_K: the 6.6 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gradientai Gradient Llama 3.1 8B Instruct 1048k GGUF?

It depends on the quant: Q4_K_S is 0.0 GB, Q3_K is 0.0 GB, Q3_K_M is 0.0 GB, IQ3_M is 0.0 GB, IQ4_NL is 0.0 GB, Q4_K_M is 0.2 GB and 16 more.

Where can I download gradientai Gradient Llama 3.1 8B Instruct 1048k GGUF?

The files are on Hugging Face in the RichardErkhov/gradientai_-_Gradient-Llama-3.1-8B-Instruct-1048k-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 →