Llama2 7B Chat Uncensored vs Llama 2 70B HF

Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.

Llama2 7B Chat Uncensored

georgesung · 6.7B

Chat
Llama 2 70B HF

Meta · 69.0B

Chat

Specifications

Llama2 7B Chat UncensoredLlama 2 70B HF
Parameters6.7B69.0B
Context2K
ArchitectureLlamaForCausalLM
LicenseOtherLlama 2 Community
Downloads1.0K15.4K
ReleasedMay 2024Apr 2024

VRAM by Quantization: Llama2 7B Chat Uncensored vs Llama 2 70B HF

QuantizationBitsLlama2 7B Chat Uncensored VRAMLlama 2 70B HF VRAM
BF1616.0014.8 GB151.8 GB

Verdict

Llama2 7B Chat Uncensored needs less VRAM at BF16 (14.8 GB vs 151.8 GB), so it fits on smaller GPUs. Llama 2 70B HF is the more widely downloaded of the two.

Frequently Asked Questions

Which needs less VRAM, Llama2 7B Chat Uncensored or Llama 2 70B HF?

At BF16, Llama2 7B Chat Uncensored needs 14.8 GB and Llama 2 70B HF needs 151.8 GB, so Llama2 7B Chat Uncensored is the lighter option to run locally.

What is the difference between Llama2 7B Chat Uncensored and Llama 2 70B HF?

Llama2 7B Chat Uncensored is a 6.7B model from georgesung (Llama 2 family), while Llama 2 70B HF is a 69.0B model from Meta (Llama 2 family). Compare their VRAM requirements above to see which fits your GPU or Mac.