YE

Yeet 51b 200k i1

YeetGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters51.1B
Context195K
Layers90
Architecturellama
Smallest quant19.5 GB
Quick answer

Yeet 51b 200k i1 needs about 34.7 GB of memory at Q4_K_M (a 31.2 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 10 quants, from 19.5 GB (Q2_K) to 42.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 12.1 GB.

Yeet 51b 200k i1 is a 51.1B-parameter Yeet model in GGUF format, quantized by mradermacher. Its trained context length is 195K tokens. The repository has 10 quant files, from 19.5 GB (Q2_K) to 42.5 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K19.5 GB 23.0 GB
Too big Get file →
Q3_K_S22.7 GB 26.2 GB
Too big Get file →
Q3_K_M25.2 GB 28.8 GB
Too big Get file →
Q3_K_L27.5 GB 31.0 GB
Too big Get file →
Q4_029.5 GB 33.0 GB
Too big Get file →
Q4_K_S29.6 GB 33.1 GB
Too big Get file →
Q4_K_M31.2 GB 34.7 GB
Too big Get file →
Q5_K_S35.8 GB 39.3 GB
Too big Get file →
Q5_K_M36.7 GB 40.2 GB
Too big Get file →
Q6_K42.5 GB 46.0 GB
Too big Get file →

What GPU do you need for Yeet 51b 200k 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: the best quant that fits is Q2_K (19.5 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q3_K_L (27.5 GB file, about 31.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (42.5 GB file, about 46.0 GB in use).

Which Yeet 51b 200k i1 quant should you choose?

Q4_K_M is the usual starting point for Yeet 51b 200k i1: it balances file size and quality well. Here it is a 31.2 GB file.

If memory is tight, the smallest file is Q2_K at 19.5 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
Parameters51.1B
Layers90
Trained context200,000 tokens
KV cache (fp16)360 KB per token

Source

Quantized bymradermacher
FamilyYeet
Licenseother
Downloads (HF)463
Last updated2024-05-06

Frequently asked questions about Yeet 51b 200k i1

How much VRAM does Yeet 51b 200k i1 need?

About 34.7 GB at Q4_K_M with an 8K context window. That is the 31.2 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 Yeet 51b 200k i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 23.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Yeet 51b 200k i1 GGUF?

It depends on the quant: Q2_K is 19.5 GB, Q3_K_S is 22.7 GB, Q3_K_M is 25.2 GB, Q3_K_L is 27.5 GB, Q4_0 is 29.5 GB, Q4_K_S is 29.6 GB and 4 more.

What context length does Yeet 51b 200k i1 support?

The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 3.0 GB at 8K and 12.1 GB at 32K.

Where can I download Yeet 51b 200k i1 GGUF?

The files are on Hugging Face in the mradermacher/Yeet_51b_200k-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 Yeet 51b 200k i1 use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Yeet_51b_200k

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Yeet models

All Yeet →

Other large models

All large models →