BE

CausalLM 35b beta long

BetaGGUF by QuantFactoryUpdated 2024-06-08
Download on Hugging Face
Parameters35B
Context8K
Layers40
Architecturellama
Smallest quant13.8 GB
Quick answer

CausalLM 35b beta long needs about 32.8 GB of memory at Q4_K_M (a 21.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 14 quants, from 13.8 GB (Q2_K) to 37.2 GB (Q8_0).

CausalLM 35b beta long is a 35B-parameter Beta model in GGUF format, quantized by QuantFactory. Its trained context length is 8K tokens. The repository has 14 quant files, from 13.8 GB (Q2_K) to 37.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K13.8 GB 25.1 GB
Too big Get file →
Q3_K_S15.9 GB 27.1 GB
Too big Get file →
Q3_K_M17.6 GB 28.9 GB
Too big Get file →
Q3_K_L19.2 GB 30.4 GB
Too big Get file →
Q4_020.2 GB 31.5 GB
Too big Get file →
Q4_K_S20.4 GB 31.6 GB
Too big Get file →
Q4_K_M21.5 GB 32.8 GB
Too big Get file →
Q4_122.3 GB 33.5 GB
Too big Get file →
Q5_024.3 GB 35.6 GB
Too big Get file →
Q5_K_S24.3 GB 35.6 GB
Too big Get file →
Q5_K_M25.0 GB 36.2 GB
Too big Get file →
Q5_126.4 GB 37.6 GB
Too big Get file →
Q6_K28.7 GB 39.9 GB
Too big Get file →
Q8_037.2 GB 48.4 GB
Too big Get file →

What GPU do you need for CausalLM 35b beta long?

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: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q4_K_S (20.4 GB file, about 31.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (28.7 GB file, about 39.9 GB in use).

Which CausalLM 35b beta long quant should you choose?

Q4_K_M is the usual starting point for CausalLM 35b beta long: it balances file size and quality well. Here it is a 21.5 GB file.

The Q8_0 file is 37.2 GB, about 1.7 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 Q2_K at 13.8 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
Parameters35B
Layers40
Trained context8,192 tokens
KV cache (fp16)1280 KB per token

Source

Quantized byQuantFactory
FamilyBeta
Licensegpl-3.0
Downloads (HF)322
Last updated2024-06-08

Frequently asked questions about CausalLM 35b beta long

How much VRAM does CausalLM 35b beta long need?

About 32.8 GB at Q4_K_M with an 8K context window. That is the 21.5 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 CausalLM 35b beta long on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 25.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of CausalLM 35b beta long GGUF?

It depends on the quant: Q2_K is 13.8 GB, Q3_K_S is 15.9 GB, Q3_K_M is 17.6 GB, Q3_K_L is 19.2 GB, Q4_0 is 20.2 GB, Q4_K_S is 20.4 GB and 8 more.

What context length does CausalLM 35b beta long support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 10.7 GB at 8K and 10.7 GB at 8K.

Where can I download CausalLM 35b beta long GGUF?

The files are on Hugging Face in the QuantFactory/CausalLM-35b-beta-long-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 CausalLM 35b beta long 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.

Other GGUFs of 35b-beta-long

Similar models

Browse all →

More from QuantFactory

All by QuantFactory →

More Beta models

All Beta →

Other large models

All large models →