WI

Winged Lagomorph 2x13B i1

WingedGGUF by mradermacherUpdated 2024-11-21
Download on Hugging Face
Parameters21.5B
Context16K
Layers40
Architecturellama
Smallest quant4.6 GB
Quick answer

Winged Lagomorph 2x13B i1 needs about 20.2 GB of memory at Q4_K_M (a 13.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 4.6 GB (IQ1_S) to 17.6 GB (Q6_K).

Winged Lagomorph 2x13B i1 is a 21.5B-parameter Winged model in GGUF format, quantized by mradermacher. Its trained context length is 16K tokens. The repository has 21 quant files, from 4.6 GB (IQ1_S) to 17.6 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S4.6 GB 11.8 GB
Too big Get file →
IQ1_M5.0 GB 12.2 GB
Too big Get file →
IQ2_XXS5.8 GB 13.0 GB
Too big Get file →
IQ2_XS6.4 GB 13.6 GB
Too big Get file →
IQ2_S6.7 GB 13.9 GB
Too big Get file →
IQ2_M7.3 GB 14.5 GB
Too big Get file →
Q2_K7.9 GB 15.1 GB
Too big Get file →
IQ3_XXS8.2 GB 15.4 GB
Too big Get file →
IQ3_XS8.8 GB 16.0 GB
Too big Get file →
IQ3_S9.3 GB 16.5 GB
Too big Get file →
Q3_K_S9.3 GB 16.5 GB
Too big Get file →
IQ3_M9.7 GB 16.9 GB
Too big Get file →
Q3_K_M10.4 GB 17.6 GB
Too big Get file →
Q3_K_L11.3 GB 18.5 GB
Too big Get file →
IQ4_XS11.5 GB 18.7 GB
Too big Get file →
Q4_012.2 GB 19.4 GB
Too big Get file →
Q4_K_S12.2 GB 19.5 GB
Too big Get file →
Q4_K_M13.0 GB 20.2 GB
Too big Get file →
Q5_K_S14.8 GB 22.0 GB
Too big Get file →
Q5_K_M15.3 GB 22.5 GB
Too big Get file →
Q6_K17.6 GB 24.9 GB
Too big Get file →

What GPU do you need for Winged Lagomorph 2x13B 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: the best quant that fits is IQ1_S (4.6 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XS (8.8 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (15.3 GB file, about 22.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (17.6 GB file, about 24.9 GB in use).

Which Winged Lagomorph 2x13B i1 quant should you choose?

Q4_K_M is the usual starting point for Winged Lagomorph 2x13B i1: it balances file size and quality well. Here it is a 13.0 GB file.

If memory is tight, the smallest file is IQ1_S at 4.6 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

Architecturellama
Parameters21.5B (approximate, mixture of experts)
Layers40
Trained context16,384 tokens
KV cache (fp16)800 KB per token

Source

Quantized bymradermacher
FamilyWinged
Licensellama2
Downloads (HF)41
Last updated2024-11-21

Frequently asked questions about Winged Lagomorph 2x13B i1

How much VRAM does Winged Lagomorph 2x13B i1 need?

About 20.2 GB at Q4_K_M with an 8K context window. That is the 13.0 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 Winged Lagomorph 2x13B i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Winged Lagomorph 2x13B i1 GGUF?

It depends on the quant: IQ1_S is 4.6 GB, IQ1_M is 5.0 GB, IQ2_XXS is 5.8 GB, IQ2_XS is 6.4 GB, IQ2_S is 6.7 GB, IQ2_M is 7.3 GB and 15 more.

What context length does Winged Lagomorph 2x13B i1 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 6.7 GB at 8K and 13.4 GB at 16K.

Where can I download Winged Lagomorph 2x13B i1 GGUF?

The files are on Hugging Face in the mradermacher/Winged-Lagomorph-2x13B-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 Winged Lagomorph 2x13B 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.

Other GGUFs of Winged-Lagomorph-2x13B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Winged models

All Winged →

Other medium models

All medium models →