AS

AstroMLab astrollama 3 8b chat aic

AstromlabGGUF by RichardErkhovUpdated 2024-10-06
Download on Hugging Face
Parameters8.03B
Context8K
Layers—
Architecturellama
Smallest quant1.2 GB
Quick answer

AstroMLab astrollama 3 8b chat aic needs about 4.7 GB of memory at IQ3_M (a 3.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 1.2 GB (Q4_K_S) to 4.7 GB (IQ4_NL).

AstroMLab astrollama 3 8b chat aic is a 8.03B-parameter Astromlab model in GGUF format, quantized by RichardErkhov. Its trained context length is 8K tokens. The repository has 12 quant files, from 1.2 GB (Q4_K_S) to 4.7 GB (IQ4_NL).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S1.2 GB 1.8 GB
Fits Get file →
Q2_K3.2 GB 4.1 GB
Fits Get file →
IQ3_XS3.5 GB 4.4 GB
Fits Get file →
Q3_K_S3.7 GB 4.6 GB
Fits Get file →
IQ3_S3.7 GB 4.6 GB
Fits Get file →
IQ3_M3.8 GB 4.7 GB
Fits Get file →
Q3_K4.0 GB 5.0 GB
Fits Get file →
Q3_K_M4.0 GB 5.0 GB
Fits Get file →
Q3_K_L4.3 GB 5.3 GB
Fits Get file →
IQ4_XS4.5 GB 5.5 GB
Fits Get file →
Q4_04.7 GB 5.7 GB
Fits Get file →
IQ4_NL4.7 GB 5.8 GB
Fits Get file →

What GPU do you need for AstroMLab astrollama 3 8b chat aic?

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 Q4_K_S (1.2 GB file, about 1.8 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_NL (4.7 GB file, about 5.8 GB in use).

Which AstroMLab astrollama 3 8b chat aic quant should you choose?

IQ3_M (3.8 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is Q4_K_S at 1.2 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
Parameters8.03B
Trained context8,192 tokens

Source

Quantized byRichardErkhov
FamilyAstromlab
Downloads (HF)10
Last updated2024-10-06

Frequently asked questions about AstroMLab astrollama 3 8b chat aic

How much VRAM does AstroMLab astrollama 3 8b chat aic need?

About 4.7 GB at IQ3_M with an 8K context window. That is the 3.8 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 AstroMLab astrollama 3 8b chat aic on an 8 GB GPU?

Yes, with IQ4_NL: the 4.7 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of AstroMLab astrollama 3 8b chat aic GGUF?

It depends on the quant: Q4_K_S is 1.2 GB, Q2_K is 3.2 GB, IQ3_XS is 3.5 GB, Q3_K_S is 3.7 GB, IQ3_S is 3.7 GB, IQ3_M is 3.8 GB and 6 more.

What context length does AstroMLab astrollama 3 8b chat aic support?

The GGUF header lists a trained context length of 8,192 tokens (8K).

Where can I download AstroMLab astrollama 3 8b chat aic GGUF?

The files are on Hugging Face in the RichardErkhov/AstroMLab_-_astrollama-3-8b-chat_aic-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 Astromlab models

All Astromlab →

Other small models

All small models →