Llama3 8B DarkIdol 2.3 Uncensored 32K vs Dolphin 2.9.1 Llama 3 70B
Side-by-side comparison of VRAM requirements, quantization, context length, and hardware compatibility.
Specifications
| Llama3 8B DarkIdol 2.3 Uncensored 32K | Dolphin 2.9.1 Llama 3 70B | |
|---|---|---|
| Parameters | 8.0B | 70.6B |
| Context | 131K | 8K |
| Architecture | LlamaForCausalLM | LlamaForCausalLM |
| License | Llama 3 Community | Llama 3 Community |
| Downloads | 2.1K | 9.0K |
| Released | Jul 2024 | Jun 2024 |
VRAM by Quantization: Llama3 8B DarkIdol 2.3 Uncensored 32K vs Dolphin 2.9.1 Llama 3 70B
| Quantization | Bits | Llama3 8B DarkIdol 2.3 Uncensored 32K VRAM | Dolphin 2.9.1 Llama 3 70B VRAM |
|---|---|---|---|
| BF16 | 16.00 | 16.6 GB | 142.1 GB |
Verdict
Llama3 8B DarkIdol 2.3 Uncensored 32K needs less VRAM at BF16 (16.6 GB vs 142.1 GB), so it fits on smaller GPUs. Llama3 8B DarkIdol 2.3 Uncensored 32K supports a longer context window (131K tokens). Dolphin 2.9.1 Llama 3 70B is the more widely downloaded of the two.
Frequently Asked Questions
- Which needs less VRAM, Llama3 8B DarkIdol 2.3 Uncensored 32K or Dolphin 2.9.1 Llama 3 70B?
At BF16, Llama3 8B DarkIdol 2.3 Uncensored 32K needs 16.6 GB and Dolphin 2.9.1 Llama 3 70B needs 142.1 GB, so Llama3 8B DarkIdol 2.3 Uncensored 32K is the lighter option to run locally.
- Which has a longer context window, Llama3 8B DarkIdol 2.3 Uncensored 32K or Dolphin 2.9.1 Llama 3 70B?
Llama3 8B DarkIdol 2.3 Uncensored 32K supports 131,072 tokens and Dolphin 2.9.1 Llama 3 70B supports 8,192 tokens.
- What is the difference between Llama3 8B DarkIdol 2.3 Uncensored 32K and Dolphin 2.9.1 Llama 3 70B?
Llama3 8B DarkIdol 2.3 Uncensored 32K is a 8.0B model from aifeifei798 (Llama 3 family), while Dolphin 2.9.1 Llama 3 70B is a 70.6B model from dphn (Llama 3 family). Compare their VRAM requirements above to see which fits your GPU or Mac.