Hermes 4.3 36B vs Hermes 4 405B
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| Hermes 4.3 36B | Hermes 4 405B | |
|---|---|---|
| Parameters | 36.2B | 405.9B |
| Context | 524K | 131K |
| Architecture | SeedOssForCausalLM | LlamaForCausalLM |
| License | Apache 2.0 | Llama 3 Community |
| Downloads | 26.7K | 546 |
| Released | Dec 2025 | Sep 2025 |
VRAM by Quantization: Hermes 4.3 36B vs Hermes 4 405B
| Quantization | Bits | Hermes 4.3 36B VRAM | Hermes 4 405B VRAM |
|---|---|---|---|
| BF16 | 16.00 | 72.9 GB | 813.1 GB |
Verdict
Hermes 4.3 36B needs less VRAM at BF16 (72.9 GB vs 813.1 GB), so it fits on smaller GPUs. Hermes 4.3 36B supports a longer context window (524K tokens). Hermes 4.3 36B is the more widely downloaded of the two.
Frequently Asked Questions
- Which needs less VRAM, Hermes 4.3 36B or Hermes 4 405B?
At BF16, Hermes 4.3 36B needs 72.9 GB and Hermes 4 405B needs 813.1 GB, so Hermes 4.3 36B is the lighter option to run locally.
- Which has a longer context window, Hermes 4.3 36B or Hermes 4 405B?
Hermes 4.3 36B supports 524,288 tokens and Hermes 4 405B supports 131,072 tokens.
- What is the difference between Hermes 4.3 36B and Hermes 4 405B?
Hermes 4.3 36B is a 36.2B model from Nous Research (Hermes family), while Hermes 4 405B is a 405.9B model from Nous Research (Hermes family). Compare their VRAM requirements above to see which fits your GPU or Mac.