BE

34b beta

BetaGGUF by LoneStrikerUpdated 2024-02-18
Download on Hugging Face
Parameters34.4B
Context195K
Layers60
Architecturellama
Smallest quant15.0 GB
Quick answer

34b beta needs about 23.2 GB of memory at Q4_K_M (a 20.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 9 quants, from 15.0 GB (Q3_K_S) to 36.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

34b beta is a 34.4B-parameter Beta model in GGUF format, quantized by LoneStriker. Its trained context length is 195K tokens. The repository has 9 quant files, from 15.0 GB (Q3_K_S) to 36.5 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S15.0 GB 17.5 GB
Too big Get file →
Q3_K_M16.7 GB 19.2 GB
Too big Get file →
Q3_K_L18.1 GB 20.7 GB
Too big Get file →
Q4_K_S19.6 GB 22.1 GB
Too big Get file →
Q4_K_M20.7 GB 23.2 GB
Too big Get file →
Q5_K_S23.7 GB 26.2 GB
Too big Get file →
Q5_K_M24.3 GB 26.8 GB
Too big Get file →
Q6_K28.2 GB 30.7 GB
Too big Get file →
Q8_036.5 GB 39.1 GB
Too big Get file →

What GPU do you need for 34b beta?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q4_K_M (20.7 GB file, about 23.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.2 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (36.5 GB file, about 39.1 GB in use).

Which 34b beta quant should you choose?

Q4_K_M is the usual starting point for 34b beta: it balances file size and quality well. Here it is a 20.7 GB file.

The Q8_0 file is 36.5 GB, about 1.8 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 Q3_K_S at 15.0 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters34.4B
Layers60
Trained context200,000 tokens
KV cache (fp16)240 KB per token

Source

Quantized byLoneStriker
FamilyBeta
Licensegpl-3.0
Downloads (HF)20
Last updated2024-02-18

Frequently asked questions about 34b beta

How much VRAM does 34b beta need?

About 23.2 GB at Q4_K_M with an 8K context window. That is the 20.7 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 34b beta on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of 34b beta GGUF?

It depends on the quant: Q3_K_S is 15.0 GB, Q3_K_M is 16.7 GB, Q3_K_L is 18.1 GB, Q4_K_S is 19.6 GB, Q4_K_M is 20.7 GB, Q5_K_S is 23.7 GB and 3 more.

What context length does 34b beta support?

The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download 34b beta GGUF?

The files are on Hugging Face in the LoneStriker/34b-beta-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does 34b beta use?

Hugging Face lists the license as gpl-3.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from LoneStriker

All by LoneStriker →

More Beta models

All Beta →

Other large models

All large models →