DA

DaringMaid 20B V1.1 i1

DaringmaidGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters20B
Context4K
Layers62
Architecturellama
Smallest quant4.6 GB
Quick answer

DaringMaid 20B V1.1 i1 needs about 23.1 GB of memory at Q4_K_M (a 12.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 22 quants, from 4.6 GB (IQ1_S) to 16.6 GB (Q6_K).

20B parameter LLaMA model with multiple IQ and Q quantizations

DaringMaid 20B V1.1 i1 is a 20‑billion parameter LLaMA model. It offers a range of quantized GGUF files from IQ1_S to Q6_K. The model is licensed under cc‑by‑nc‑4.0 and supports a 4096 token context window.

Good at

  • Large context handling
  • Wide range of quant options
  • High parameter count

Limits

  • No vision support
  • cc‑by‑nc‑4.0 license restricts commercial use
  • Requires 8‑k context for memory estimates

Best for

  • Fine‑tuning on custom datasets
  • Running on GPUs with 8‑k context
  • Exploring quantization trade‑offs

Who it’s for. Developers and researchers who need a large LLaMA model with flexible quantization. The model is suitable for local inference on GPUs that support GGUF files.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S4.6 GB 10.3 GB
Too big Get file →
IQ1_M4.8 GB 10.5 GB
Too big Get file →
IQ2_XXS5.6 GB 11.3 GB
Too big Get file →
IQ2_XS6.2 GB 11.9 GB
Too big Get file →
IQ2_S6.6 GB 12.3 GB
Too big Get file →
IQ2_M7.1 GB 12.8 GB
Too big Get file →
Q2_K7.6 GB 13.3 GB
Too big Get file →
IQ3_XXS7.8 GB 13.5 GB
Too big Get file →
IQ3_XS8.4 GB 14.1 GB
Too big Get file →
IQ3_S8.9 GB 14.6 GB
Too big Get file →
Q3_K_S8.9 GB 14.6 GB
Too big Get file →
IQ3_M9.3 GB 15.1 GB
Too big Get file →
Q3_K_M9.9 GB 15.6 GB
Too big Get file →
Q3_K_L10.8 GB 16.5 GB
Too big Get file →
IQ4_XS10.9 GB 16.6 GB
Too big Get file →
IQ4_NL11.5 GB 17.2 GB
Too big Get file →
Q4_011.5 GB 17.2 GB
Too big Get file →
Q4_K_S11.6 GB 17.3 GB
Too big Get file →
Q4_K_M12.2 GB 17.9 GB
Too big Get file →
Q5_K_S14.0 GB 19.7 GB
Too big Get file →
Q5_K_M14.4 GB 20.1 GB
Too big Get file →
Q6_K16.6 GB 22.3 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (4.61 GB file, 15.5 GB memory). For 12‑GB VRAM, IQ2_S (6.61 GB file, 17.5 GB memory). For 24‑GB VRAM, Q5_K_M (14.35 GB file, 25.3 GB memory). Memory estimates are approximate.

What GPU do you need for DaringMaid 20B V1.1 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_M (4.8 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (12.2 GB file, about 23.1 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (16.6 GB file, about 27.5 GB in use).

Which DaringMaid 20B V1.1 i1 quant should you choose?

Q4_K_M is the usual starting point for DaringMaid 20B V1.1 i1: it balances file size and quality well. Here it is a 12.2 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
Parameters20B
Layers62
Trained context4,096 tokens
KV cache (fp16)1240 KB per token

Source

Quantized bymradermacher
Downloads (HF)2,808
Last updated2024-05-06

Frequently asked questions about DaringMaid 20B V1.1 i1

How much VRAM does DaringMaid 20B V1.1 i1 need?

About 23.1 GB at Q4_K_M with an 8K context window. That is the 12.2 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 DaringMaid 20B V1.1 i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DaringMaid 20B V1.1 i1 GGUF?

It depends on the quant: IQ1_S is 4.6 GB, IQ1_M is 4.8 GB, IQ2_XXS is 5.6 GB, IQ2_XS is 6.2 GB, IQ2_S is 6.6 GB, IQ2_M is 7.1 GB and 16 more.

What context length does DaringMaid 20B V1.1 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 10.4 GB at 8K and 5.2 GB at 4K.

Where can I download DaringMaid 20B V1.1 i1 GGUF?

The files are on Hugging Face in the mradermacher/DaringMaid-20B-V1.1-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 DaringMaid 20B V1.1 i1 use?

Hugging Face lists the license as cc-by-nc-4.0. 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 DaringMaid 20B on 8 GB VRAM?

Use the IQ1_S quant, which requires about 15.5 GB memory at 8‑k context.

What license does this model use?

The model is licensed under cc‑by‑nc‑4.0, which allows non‑commercial use.

Does the model support vision tasks?

No, the model does not have vision capabilities.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Daringmaid models

All Daringmaid →

Other medium models

All medium models →