Dolphin 2.9.1 Llama 3 70B vs Llama 3.1 405B

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

Dolphin 2.9.1 Llama 3 70B

dphn · 70.6B

Chat
Llama 3.1 405B

Meta · 405B

Chat

Specifications

Dolphin 2.9.1 Llama 3 70BLlama 3.1 405B
Parameters70.6B405B
Context8K
ArchitectureLlamaForCausalLM
LicenseLlama 3 CommunityLlama 3.1 Community
Downloads9.0K514.6K
ReleasedJun 2024Sep 2024

VRAM by Quantization: Dolphin 2.9.1 Llama 3 70B vs Llama 3.1 405B

QuantizationBitsDolphin 2.9.1 Llama 3 70B VRAMLlama 3.1 405B VRAM
BF1616.00142.1 GB891 GB

Verdict

Dolphin 2.9.1 Llama 3 70B needs less VRAM at BF16 (142.1 GB vs 891.0 GB), so it fits on smaller GPUs. Llama 3.1 405B is the more widely downloaded of the two.

Frequently Asked Questions

Which needs less VRAM, Dolphin 2.9.1 Llama 3 70B or Llama 3.1 405B?

At BF16, Dolphin 2.9.1 Llama 3 70B needs 142.1 GB and Llama 3.1 405B needs 891.0 GB, so Dolphin 2.9.1 Llama 3 70B is the lighter option to run locally.

What is the difference between Dolphin 2.9.1 Llama 3 70B and Llama 3.1 405B?

Dolphin 2.9.1 Llama 3 70B is a 70.6B model from dphn (Llama 3 family), while Llama 3.1 405B is a 405B model from Meta (Llama 3 family). Compare their VRAM requirements above to see which fits your GPU or Mac.