MegaDolphin 120b i1 needs about 42.3 GB of memory at IQ2_S (a 37.1 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 9 quants, from 25.6 GB (IQ1_S) to 49.2 GB (IQ3_XS).
MegaDolphin 120b i1 – a large llama-based model with 120B parameters
MegaDolphin 120b i1 is a 120‑billion‑parameter llama model. It supports a 4096‑token context window and is released under the llama2 license. The model is available in multiple quantizations for different memory budgets.
Good at
- Long‑form conversation
- Personal advice and empathy
- Uncensored responses
Limits
- No vision support
- Requires large VRAM for full precision
- No alignment layer included
Best for
- Chatbots needing deep context
- Research on large‑scale language models
- Custom fine‑tuning projects
Who it’s for. Developers and researchers who need a large llama model for text‑only applications. The model is suitable for those who can provide the necessary GPU memory and are comfortable adding their own alignment layer.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 25.6 GB | 28.4 GB | Too big | Get file → | |
| IQ1_M | 27.7 GB | 30.5 GB | Too big | Get file → | |
| IQ2_XXS | 32.1 GB | 35.0 GB | Too big | Get file → | |
| IQ2_XS | 35.7 GB | 38.6 GB | Too big | Get file → | |
| IQ2_S | 37.1 GB | 40.0 GB | Too big | Get file → | |
| IQ2_M | 40.4 GB | 43.3 GB | Too big | Get file → | |
| Q2_K | 44.5 GB | 47.3 GB | Too big | Get file → | |
| IQ3_XXS | 47.2 GB | 50.0 GB | Too big | Get file → | |
| IQ3_XS | 49.2 GB | 52.0 GB | Too big | Get file → |
For 8 GB VRAM use IQ1_S (25.57 GB file, ~30.8 GB memory at 8k context). For 12 GB VRAM use IQ1_M (27.69 GB file, ~32.9 GB memory). For 16 GB VRAM use IQ2_XXS (32.14 GB file, ~37.3 GB memory).
What GPU do you need for MegaDolphin 120b i1?
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: the best quant that fits is IQ1_S (25.6 GB file, about 30.8 GB in use).
- 48 GB VRAM: the best quant that fits is IQ2_M (40.4 GB file, about 45.6 GB in use).
Which MegaDolphin 120b i1 quant should you choose?
IQ2_S (37.1 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
If memory is tight, the smallest file is IQ1_S at 25.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MegaDolphin 120b i1
How much VRAM does MegaDolphin 120b i1 need?
About 42.3 GB at IQ2_S with an 8K context window. That is the 37.1 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 MegaDolphin 120b i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 30.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of MegaDolphin 120b i1 GGUF?
It depends on the quant: IQ1_S is 25.6 GB, IQ1_M is 27.7 GB, IQ2_XXS is 32.1 GB, IQ2_XS is 35.7 GB, IQ2_S is 37.1 GB, IQ2_M is 40.4 GB and 3 more.
What context length does MegaDolphin 120b i1 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.7 GB at 8K and 2.3 GB at 4K.
Where can I download MegaDolphin 120b i1 GGUF?
The files are on Hugging Face in the mradermacher/MegaDolphin-120b-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does MegaDolphin 120b i1 use?
Hugging Face lists the license as llama2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run MegaDolphin 120b i1 on 8 GB VRAM?
Use the IQ1_S quantization; it requires about 30.8 GB of VRAM at 8k context, so 8 GB is insufficient. You need at least 30 GB VRAM for that quant.
Does this model support vision?
No, the model has no vision capabilities. It is text‑only.
Is the model licensed for commercial use?
It is released under the llama2 license, which allows commercial use with the usual conditions.