CA

CausalLM 34b beta iMat

CausallmGGUF by dranger003Updated 2024-02-18
Download on Hugging Face
Parameters34.4B
Context195K
Layers60
Architecturellama
Smallest quant9.3 GB
Quick answer

CausalLM 34b beta iMat 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 4 quants, from 9.3 GB (IQ2_XXS) to 20.7 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

CausalLM 34b beta iMat is a 34.4B-parameter Causallm model in GGUF format, quantized by dranger003. Its trained context length is 195K tokens. The repository has 4 quant files, from 9.3 GB (IQ2_XXS) to 20.7 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS9.3 GB 11.8 GB
Too big Get file →
IQ2_XS10.3 GB 12.8 GB
Too big Get file →
IQ3_XXS13.7 GB 16.2 GB
Too big Get file →
Q4_K_M20.7 GB 23.2 GB
Too big Get file →

What GPU do you need for CausalLM 34b beta iMat?

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: the best quant that fits is IQ2_XXS (9.3 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ2_XS (10.3 GB file, about 12.8 GB in use).
  • 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 beta iMat quant should you choose?

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

If memory is tight, the smallest file is IQ2_XXS at 9.3 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
Parameters34.4B
Layers60
Trained context200,000 tokens
KV cache (fp16)240 KB per token

Source

Quantized bydranger003
FamilyCausallm
Licensegpl-3.0
Downloads (HF)100
Last updated2024-02-18

Frequently asked questions about CausalLM 34b beta iMat

How much VRAM does CausalLM 34b beta iMat 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 beta iMat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of CausalLM 34b beta iMat GGUF?

It depends on the quant: IQ2_XXS is 9.3 GB, IQ2_XS is 10.3 GB, IQ3_XXS is 13.7 GB, Q4_K_M is 20.7 GB.

What context length does CausalLM 34b beta iMat 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 CausalLM 34b beta iMat GGUF?

The files are on Hugging Face in the dranger003/CausalLM-34b-beta-iMat.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 34b beta iMat 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 dranger003

All by dranger003 →

More Causallm models

All Causallm →

Other large models

All large models →