LA

latxa 7b v1

LatxaGGUF by r3v1Updated 2024-02-23
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant2.8 GB
Quick answer

latxa 7b v1 needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 2.8 GB (Q2_K) to 13.5 GB (F16).

latxa 7b v1 is a 6.74B-parameter Latxa model in GGUF format, quantized by r3v1. Its trained context length is 4K tokens. The repository has 3 quant files, from 2.8 GB (Q2_K) to 13.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.8 GB 5.5 GB
Fits Get file →
Q4_K_M4.1 GB 6.7 GB
Fits Get file →
F1613.5 GB 16.1 GB
Too big Get file →

What GPU do you need for latxa 7b v1?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q2_K (2.8 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (4.1 GB file, about 8.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (4.1 GB file, about 8.9 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (13.5 GB file, about 18.3 GB in use).

Which latxa 7b v1 quant should you choose?

Q4_K_M is the usual starting point for latxa 7b v1: it balances file size and quality well. Here it is a 4.1 GB file.

If memory is tight, the smallest file is Q2_K at 2.8 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byr3v1
FamilyLatxa
Downloads (HF)9
Last updated2024-02-23

Frequently asked questions about latxa 7b v1

How much VRAM does latxa 7b v1 need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 latxa 7b v1 on an 8 GB GPU?

Yes, with Q2_K: the 2.8 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 latxa 7b v1 GGUF?

It depends on the quant: Q2_K is 2.8 GB, Q4_K_M is 4.1 GB, F16 is 13.5 GB.

What context length does latxa 7b v1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download latxa 7b v1 GGUF?

The files are on Hugging Face in the r3v1/latxa-7b-v1-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 r3v1

All by r3v1 →

More Latxa models

All Latxa →

Other small models

All small models →