Dolphin 2.9.1 Llama 3 70B vs Llama3 8B 1.58 100B Tokens
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| Dolphin 2.9.1 Llama 3 70B | Llama3 8B 1.58 100B Tokens | |
|---|---|---|
| Parameters | 70.6B | 2.8B |
| Context | 8K | 8K |
| Architecture | LlamaForCausalLM | LlamaForCausalLM |
| License | Llama 3 Community | — |
| Downloads | 9.0K | 1.6K |
| Released | Jun 2024 | Sep 2024 |
VRAM by Quantization: Dolphin 2.9.1 Llama 3 70B vs Llama3 8B 1.58 100B Tokens
| Quantization | Bits | Dolphin 2.9.1 Llama 3 70B VRAM | Llama3 8B 1.58 100B Tokens VRAM |
|---|---|---|---|
| BF16 | 16.00 | 142.1 GB | 6.2 GB |
Verdict
Llama3 8B 1.58 100B Tokens needs less VRAM at BF16 (6.2 GB vs 142.1 GB), so it fits on smaller GPUs. 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 Llama3 8B 1.58 100B Tokens?
At BF16, Dolphin 2.9.1 Llama 3 70B needs 142.1 GB and Llama3 8B 1.58 100B Tokens needs 6.2 GB, so Llama3 8B 1.58 100B Tokens is the lighter option to run locally.
- Which has a longer context window, Dolphin 2.9.1 Llama 3 70B or Llama3 8B 1.58 100B Tokens?
Dolphin 2.9.1 Llama 3 70B supports 8,192 tokens and Llama3 8B 1.58 100B Tokens supports 8,192 tokens.
- What is the difference between Dolphin 2.9.1 Llama 3 70B and Llama3 8B 1.58 100B Tokens?
Dolphin 2.9.1 Llama 3 70B is a 70.6B model from dphn (Llama 3 family), while Llama3 8B 1.58 100B Tokens is a 2.8B model from HF1BitLLM (Llama 3 family). Compare their VRAM requirements above to see which fits your GPU or Mac.