ME

megameditron 120b i1

MegameditronGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters120B
Context4K
Layers140
Architecturellama
Smallest quant26.1 GB
Quick answer

megameditron 120b i1 needs about 41.4 GB of memory at IQ2_XS (a 36.2 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 8 quants, from 26.1 GB (IQ1_S) to 47.0 GB (IQ3_XXS).

megameditron 120b i1 is a 120B-parameter Megameditron model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 8 quant files, from 26.1 GB (IQ1_S) to 47.0 GB (IQ3_XXS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S26.1 GB 28.9 GB
Too big Get file →
IQ1_M28.6 GB 31.4 GB
Too big Get file →
IQ2_XXS32.7 GB 35.5 GB
Too big Get file →
IQ2_XS36.2 GB 39.1 GB
Too big Get file →
IQ2_S38.0 GB 40.9 GB
Too big Get file →
IQ2_M41.3 GB 44.1 GB
Too big Get file →
Q2_K45.0 GB 47.9 GB
Too big Get file →
IQ3_XXS47.0 GB 49.9 GB
Too big Get file →

What GPU do you need for megameditron 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 megameditron 120b i1 quant should you choose?

IQ2_XS (36.2 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

Architecturellama
Parameters120B
Layers140
Trained context4,096 tokens
KV cache (fp16)560 KB per token

Source

Quantized bymradermacher
Downloads (HF)54
Last updated2024-05-06

Frequently asked questions about megameditron 120b i1

How much VRAM does megameditron 120b i1 need?

About 41.4 GB at IQ2_XS with an 8K context window. That is the 36.2 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 megameditron 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 megameditron 120b i1 GGUF?

It depends on the quant: IQ1_S is 26.1 GB, IQ1_M is 28.6 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 and 2 more.

What context length does megameditron 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 megameditron 120b i1 GGUF?

The files are on Hugging Face in the mradermacher/megameditron-120b-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of megameditron-120b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Megameditron models

All Megameditron →

Other large models

All large models →