Dolphin 2.9.1 Llama 3 70B vs Meta Llama 3 70B Instruct Abliterated V3.5

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

Specifications

Dolphin 2.9.1 Llama 3 70BMeta Llama 3 70B Instruct Abliterated V3.5
Parameters70.6B70.6B
Context8K8K
ArchitectureLlamaForCausalLMLlamaForCausalLM
LicenseLlama 3 CommunityLlama 3 Community
Downloads9.0K8.6K
ReleasedJun 2024May 2024

VRAM by Quantization: Dolphin 2.9.1 Llama 3 70B vs Meta Llama 3 70B Instruct Abliterated V3.5

QuantizationBitsDolphin 2.9.1 Llama 3 70B VRAMMeta Llama 3 70B Instruct Abliterated V3.5 VRAM
BF1616.00142.1 GB142.1 GB

Verdict

Dolphin 2.9.1 Llama 3 70B is the more widely downloaded of the two.

Frequently Asked Questions

Which needs less VRAM, Dolphin 2.9.1 Llama 3 70B or Meta Llama 3 70B Instruct Abliterated V3.5?

At BF16, Dolphin 2.9.1 Llama 3 70B needs 142.1 GB and Meta Llama 3 70B Instruct Abliterated V3.5 needs 142.1 GB, so Dolphin 2.9.1 Llama 3 70B is the lighter option to run locally.

Which has a longer context window, Dolphin 2.9.1 Llama 3 70B or Meta Llama 3 70B Instruct Abliterated V3.5?

Dolphin 2.9.1 Llama 3 70B supports 8,192 tokens and Meta Llama 3 70B Instruct Abliterated V3.5 supports 8,192 tokens.

What is the difference between Dolphin 2.9.1 Llama 3 70B and Meta Llama 3 70B Instruct Abliterated V3.5?

Dolphin 2.9.1 Llama 3 70B is a 70.6B model from dphn (Llama 3 family), while Meta Llama 3 70B Instruct Abliterated V3.5 is a 70.6B model from failspy (Llama 3 family). Compare their VRAM requirements above to see which fits your GPU or Mac.