Llama 3.1 70B vs Hermes 3 Llama 3.1 8B
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| Llama 3.1 70B | Hermes 3 Llama 3.1 8B | |
|---|---|---|
| Parameters | 70.6B | 8.0B |
| Context | — | 131K |
| Architecture | — | LlamaForCausalLM |
| License | Llama 3.1 Community | Llama 3 Community |
| Downloads | 90.8K | 248.3K |
| Released | Sep 2024 | Sep 2024 |
VRAM by Quantization: Llama 3.1 70B vs Hermes 3 Llama 3.1 8B
| Quantization | Bits | Llama 3.1 70B VRAM | Hermes 3 Llama 3.1 8B VRAM |
|---|---|---|---|
| Q2_K | 3.40 | 33.0 GB | 4.0 GB |
| Q3_K_M | 3.90 | 37.8 GB | 4.5 GB |
| Q3_K_S | 3.50 | 34.0 GB | 4.1 GB |
| Q4_K_M | 4.80 | 46.6 GB | 5.4 GB |
| Q5_K_M | 5.70 | 55.3 GB | 6.3 GB |
| Q6_K | 6.60 | 64.0 GB | 7.2 GB |
| Q8_0 | 8.00 | 77.6 GB | 8.6 GB |
Verdict
Hermes 3 Llama 3.1 8B needs less VRAM at Q4_K_M (5.4 GB vs 46.6 GB), so it fits on smaller GPUs. Hermes 3 Llama 3.1 8B is the more widely downloaded of the two.
Frequently Asked Questions
- Which needs less VRAM, Llama 3.1 70B or Hermes 3 Llama 3.1 8B?
At Q4_K_M, Llama 3.1 70B needs 46.6 GB and Hermes 3 Llama 3.1 8B needs 5.4 GB, so Hermes 3 Llama 3.1 8B is the lighter option to run locally.
- What is the difference between Llama 3.1 70B and Hermes 3 Llama 3.1 8B?
Llama 3.1 70B is a 70.6B model from Meta (Llama 3 family), while Hermes 3 Llama 3.1 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.