giant macaroni 120b i1 needs about 43.2 GB of memory at IQ2_S (a 38.0 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 7 quants, from 26.1 GB (IQ1_S) to 47.0 GB (IQ3_XXS).
Giant Macaroni 120B i1 – a large merged LLM
Giant Macaroni 120B i1 is a 120‑billion parameter auto‑regressive model built by merging three 70B finetuned models. It is designed for logic and reasoning tasks and is available in multiple GGUF quantizations. The model uses a 4096‑token context window and is licensed under llama2.
Good at
- Logic and reasoning
- Large context handling
- Multi‑model fusion
Limits
- No vision support
- Requires large VRAM for full precision
- License restricts commercial use
Best for
- Complex reasoning prompts
- Long‑form text generation
- Academic research
Who it’s for. Researchers and developers needing a high‑capacity language model for reasoning tasks. The model is suitable for those who can run it on GPUs with sufficient VRAM and are comfortable with GGUF format.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 26.1 GB | 28.9 GB | Too big | Get file → | |
| IQ2_XXS | 32.7 GB | 35.5 GB | Too big | Get file → | |
| IQ2_XS | 36.2 GB | 39.1 GB | Too big | Get file → | |
| IQ2_S | 38.0 GB | 40.9 GB | Too big | Get file → | |
| IQ2_M | 41.3 GB | 44.1 GB | Too big | Get file → | |
| Q2_K | 45.0 GB | 47.9 GB | Too big | Get file → | |
| IQ3_XXS | 47.0 GB | 49.9 GB | Too big | Get file → |
For 8 GB VRAM, the IQ1_S quant (26.09 GB file, 31.3 GB memory at 8k context) is the smallest option. If you have 12 GB VRAM, IQ2_XXS (32.67 GB file, 37.9 GB memory) or IQ2_XS (36.25 GB file, 41.4 GB memory) are viable. For 16 GB VRAM, consider IQ2_S (38 GB file, 43.2 GB memory) or IQ2_M (41.29 GB file, 46.5 GB memory).
What GPU do you need for giant macaroni 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 (26.1 GB file, about 31.3 GB in use).
- 48 GB VRAM: the best quant that fits is IQ2_M (41.3 GB file, about 46.5 GB in use).
Which giant macaroni 120b i1 quant should you choose?
IQ2_S (38.0 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 26.1 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 giant macaroni 120b i1
How much VRAM does giant macaroni 120b i1 need?
About 43.2 GB at IQ2_S with an 8K context window. That is the 38.0 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 giant macaroni 120b i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 31.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of giant macaroni 120b i1 GGUF?
It depends on the quant: IQ1_S is 26.1 GB, IQ2_XXS is 32.7 GB, IQ2_XS is 36.2 GB, IQ2_S is 38.0 GB, IQ2_M is 41.3 GB, Q2_K is 45.0 GB and 1 more.
What context length does giant macaroni 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 giant macaroni 120b i1 GGUF?
The files are on Hugging Face in the mradermacher/giant-macaroni-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 giant macaroni 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 Giant Macaroni 120B i1 on 8 GB VRAM?
The smallest quant, IQ1_S, requires about 31.3 GB memory at 8k context, so 8 GB VRAM is insufficient.
What is the context length of this model?
The model supports a 4096‑token context window.
Is this model licensed for commercial use?
It is licensed under llama2, which restricts commercial deployment.