Dolphin 2.9.1 Llama 3 70B vs Human Like LLama3 8B Instruct
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| Dolphin 2.9.1 Llama 3 70B | Human Like LLama3 8B Instruct | |
|---|---|---|
| Parameters | 70.6B | 8.0B |
| Context | 8K | 8K |
| Architecture | LlamaForCausalLM | LlamaForCausalLM |
| License | Llama 3 Community | Llama 3 Community |
| Downloads | 9.0K | 105 |
| Released | Jun 2024 | Jan 2026 |
VRAM by Quantization: Dolphin 2.9.1 Llama 3 70B vs Human Like LLama3 8B Instruct
| Quantization | Bits | Dolphin 2.9.1 Llama 3 70B VRAM | Human Like LLama3 8B Instruct VRAM |
|---|---|---|---|
| BF16 | 16.00 | 142.1 GB | 16.6 GB |
Verdict
Human Like LLama3 8B Instruct needs less VRAM at BF16 (16.6 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 Human Like LLama3 8B Instruct?
At BF16, Dolphin 2.9.1 Llama 3 70B needs 142.1 GB and Human Like LLama3 8B Instruct needs 16.6 GB, so Human Like LLama3 8B Instruct is the lighter option to run locally.
- Which has a longer context window, Dolphin 2.9.1 Llama 3 70B or Human Like LLama3 8B Instruct?
Dolphin 2.9.1 Llama 3 70B supports 8,192 tokens and Human Like LLama3 8B Instruct supports 8,192 tokens.
- What is the difference between Dolphin 2.9.1 Llama 3 70B and Human Like LLama3 8B Instruct?
Dolphin 2.9.1 Llama 3 70B is a 70.6B model from dphn (Llama 3 family), while Human Like LLama3 8B Instruct is a 8.0B model from HumanLLMs (Llama 3 family). Compare their VRAM requirements above to see which fits your GPU or Mac.