Llama 3.3 70B Instruct vs Hermes 2 Pro Llama 3 8B

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

Llama 3.3 70B Instruct

Meta · 70.6B

Chat
Hermes 2 Pro Llama 3 8B

Nous Research · 8.0B

Chat

Specifications

Llama 3.3 70B InstructHermes 2 Pro Llama 3 8B
Parameters70.6B8.0B
Context131K8K
ArchitectureLlamaForCausalLM
Licensellama3.3Llama 3 Community
Downloads802.3K15.7K
ReleasedDec 2024Sep 2024

VRAM by Quantization: Llama 3.3 70B Instruct vs Hermes 2 Pro Llama 3 8B

QuantizationBitsLlama 3.3 70B Instruct VRAMHermes 2 Pro Llama 3 8B VRAM
Q2_K3.4033.0 GB
Q3_K_M3.9037.8 GB
Q3_K_S3.5034.0 GB
Q4_04.0038.8 GB
Q4_K_M4.8046.6 GB
Q5_K_M5.7055.3 GB
Q6_K6.6064.0 GB
Q8_08.0077.6 GB

Verdict

Llama 3.3 70B Instruct supports a longer context window (131K tokens). Llama 3.3 70B Instruct is the more widely downloaded of the two.

Frequently Asked Questions

Which has a longer context window, Llama 3.3 70B Instruct or Hermes 2 Pro Llama 3 8B?

Llama 3.3 70B Instruct supports 131,072 tokens and Hermes 2 Pro Llama 3 8B supports 8,192 tokens.

What is the difference between Llama 3.3 70B Instruct and Hermes 2 Pro Llama 3 8B?

Llama 3.3 70B Instruct is a 70.6B model from Meta (Llama 3 family), while Hermes 2 Pro Llama 3 8B is a 8.0B model from Nous Research (Llama 3 family). Compare their VRAM requirements above to see which fits your GPU or Mac.