LLama 3 Mega Dolphin 2.9.1 120b needs about 105.2 GB of memory at Q6_K (a 100.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds.
LLama 3 Mega Dolphin 2.9.1 120b is a 122B-parameter Llama model in GGUF format, quantized by DarqueDante. Its trained context length is 8K tokens. The repository has 1 quant file, from 100.0 GB (Q6_K) to 100.0 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 100.0 GB (5 parts) | 105.2 GB | Too big | Get file → |
What GPU do you need for LLama 3 Mega Dolphin 2.9.1 120b?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which LLama 3 Mega Dolphin 2.9.1 120b quant should you choose?
Q6_K (100.0 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LLama 3 Mega Dolphin 2.9.1 120b
How much VRAM does LLama 3 Mega Dolphin 2.9.1 120b need?
About 105.2 GB at Q6_K with an 8K context window. That is the 100.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run LLama 3 Mega Dolphin 2.9.1 120b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 105.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of LLama 3 Mega Dolphin 2.9.1 120b GGUF?
It depends on the quant: Q6_K is 100.0 GB.
What context length does LLama 3 Mega Dolphin 2.9.1 120b support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 4.7 GB at 8K and 4.7 GB at 8K.
Where can I download LLama 3 Mega Dolphin 2.9.1 120b GGUF?
The files are on Hugging Face in the DarqueDante/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.