UL

ultiima 52B i1

UltiimaGGUF by mradermacherUpdated 2025-02-04
Download on Hugging Face
Parameters52.3B
Context128K
Layers104
Architectureqwen2
Smallest quant11.3 GB
Quick answer

ultiima 52B i1 needs about 35.6 GB of memory at Q4_K_M (a 31.6 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 23 quants, from 11.3 GB (IQ1_S) to 42.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 14.0 GB.

ultiima 52B i1 is a 52.3B-parameter Ultiima model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 23 quant files, from 11.3 GB (IQ1_S) to 42.9 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S11.3 GB 15.3 GB
Too big Get file →
IQ1_M12.4 GB 16.4 GB
Too big Get file →
IQ2_XXS14.2 GB 18.2 GB
Too big Get file →
IQ2_XS15.7 GB 19.7 GB
Too big Get file →
IQ2_S16.3 GB 20.3 GB
Too big Get file →
IQ2_M17.8 GB 21.7 GB
Too big Get file →
Q2_K_S18.1 GB 22.1 GB
Too big Get file →
Q2_K19.4 GB 23.4 GB
Too big Get file →
IQ3_XXS20.3 GB 24.3 GB
Too big Get file →
IQ3_XS21.7 GB 25.6 GB
Too big Get file →
Q3_K_S22.8 GB 26.8 GB
Too big Get file →
IQ3_S22.8 GB 26.8 GB
Too big Get file →
IQ3_M23.5 GB 27.4 GB
Too big Get file →
Q3_K_M25.3 GB 29.3 GB
Too big Get file →
Q3_K_L27.4 GB 31.4 GB
Too big Get file →
IQ4_XS28.1 GB 32.1 GB
Too big Get file →
Q4_029.7 GB 33.7 GB
Too big Get file →
Q4_K_S29.8 GB 33.8 GB
Too big Get file →
Q4_K_M31.6 GB 35.6 GB
Too big Get file →
Q4_132.8 GB 36.8 GB
Too big Get file →
Q5_K_S36.0 GB 40.0 GB
Too big Get file →
Q5_K_M37.1 GB 41.1 GB
Too big Get file →
Q6_K42.9 GB 46.9 GB
Too big Get file →

What GPU do you need for ultiima 52B 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: the best quant that fits is IQ1_S (11.3 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q2_K (19.4 GB file, about 23.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q3_K_L (27.4 GB file, about 31.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (42.9 GB file, about 46.9 GB in use).

Which ultiima 52B i1 quant should you choose?

Q4_K_M is the usual starting point for ultiima 52B i1: it balances file size and quality well. Here it is a 31.6 GB file.

If memory is tight, the smallest file is IQ1_S at 11.3 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

Architectureqwen2
Parameters52.3B
Layers104
Trained context131,072 tokens
KV cache (fp16)416 KB per token

Source

Quantized bymradermacher
FamilyUltiima
Downloads (HF)32
Last updated2025-02-04

Frequently asked questions about ultiima 52B i1

How much VRAM does ultiima 52B i1 need?

About 35.6 GB at Q4_K_M with an 8K context window. That is the 31.6 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 ultiima 52B i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ultiima 52B i1 GGUF?

It depends on the quant: IQ1_S is 11.3 GB, IQ1_M is 12.4 GB, IQ2_XXS is 14.2 GB, IQ2_XS is 15.7 GB, IQ2_S is 16.3 GB, IQ2_M is 17.8 GB and 17 more.

What context length does ultiima 52B i1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.5 GB at 8K and 14.0 GB at 32K.

Where can I download ultiima 52B i1 GGUF?

The files are on Hugging Face in the mradermacher/ultiima-52B-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 ultiima-52B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Ultiima models

All Ultiima →

Other large models

All large models →