CA

CausalLM 34B preview

CausallmGGUF by mishimaUpdated 2023-12-05
Download on Hugging Face
Parameters34.4B
Context4K
Layers60
Architecturellama
Smallest quant20.7 GB
Quick answer

CausalLM 34B preview 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.

CausalLM 34B preview is a 34.4B-parameter Causallm model in GGUF format, quantized by mishima. Its trained context length is 4K tokens. The repository has 1 quant file, from 20.7 GB (Q4_K_M) to 20.7 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M20.7 GB 22.2 GB
Too big Get file →

What GPU do you need for CausalLM 34B preview?

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).

Which CausalLM 34B preview quant should you choose?

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

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters34.4B
Layers60
Trained context4,096 tokens
KV cache (fp16)240 KB per token

Source

Quantized bymishima
FamilyCausallm
Downloads (HF)8
Last updated2023-12-05

Frequently asked questions about CausalLM 34B preview

How much VRAM does CausalLM 34B preview 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 CausalLM 34B preview on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 23.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of CausalLM 34B preview GGUF?

It depends on the quant: Q4_K_M is 20.7 GB.

What context length does CausalLM 34B preview support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.0 GB at 8K and 1.0 GB at 4K.

Where can I download CausalLM 34B preview GGUF?

The files are on Hugging Face in the mishima/CausalLM-34B-preview.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 mishima

All by mishima →

More Causallm models

All Causallm →

Other large models

All large models →