Llama 68M vs Llama Guard 3 8B

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

Llama 68M

JackFram · 68M

Chat
Llama Guard 3 8B

Meta · 8.0B

Chat

Specifications

Llama 68MLlama Guard 3 8B
Parameters68M8.0B
Context2K
ArchitectureLlamaForCausalLM
LicenseApache 2.0Llama 3.1 Community
Downloads203.4K53.9K
ReleasedJun 2026Oct 2024

VRAM by Quantization: Llama 68M vs Llama Guard 3 8B

QuantizationBitsLlama 68M VRAMLlama Guard 3 8B VRAM
Q2_K3.400.0 GB3.8 GB
Q3_K_M3.900.0 GB4.3 GB
Q3_K_S3.500.0 GB3.9 GB
Q4_04.004.4 GB
Q4_K_M4.800.0 GB5.3 GB
Q5_K_M5.700.1 GB6.3 GB
Q6_K6.600.1 GB7.3 GB
Q8_08.000.1 GB8.8 GB

Verdict

Llama 68M needs less VRAM at Q4_K_M (0.0 GB vs 5.3 GB), so it fits on smaller GPUs. Llama 68M is the more widely downloaded of the two.

Frequently Asked Questions

Which needs less VRAM, Llama 68M or Llama Guard 3 8B?

At Q4_K_M, Llama 68M needs 0.0 GB and Llama Guard 3 8B needs 5.3 GB, so Llama 68M is the lighter option to run locally.

What is the difference between Llama 68M and Llama Guard 3 8B?

Llama 68M is a 68M model from JackFram (Llama family), while Llama Guard 3 8B is a 8.0B model from Meta (Llama family). Compare their VRAM requirements above to see which fits your GPU or Mac.