AE

aegolius acadicus 24b v2 i1

AegoliusGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters24.2B
Context32K
Layers32
Architecturellama
Smallest quant5.0 GB
Quick answer

aegolius acadicus 24b v2 i1 needs about 16.2 GB of memory at Q4_K_M (a 14.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 5.0 GB (IQ1_S) to 19.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

24B MOE Llama‑style model for knowledge tasks

aegolius acadicus 24b v2 i1 is a 24.2B parameter mixture‑of‑experts model built on Llama architecture. It merges fine‑tuned Llama2 and Mistral models. The model supports 32768 token context and is released under Apache‑2.0.

Good at

  • Knowledge‑heavy dialogue
  • Multi‑disciplinary reasoning
  • Fine‑tuned Llama2/Mistral content

Limits

  • No vision support
  • Requires large VRAM for higher quants
  • No explicit language support beyond English

Best for

  • Research assistants
  • Academic writing aid
  • Technical documentation generation

Who it’s for. Developers and researchers who need a large, MOE‑based language model for English‑only knowledge work. The model is suitable for environments with sufficient GPU memory and a need for fine‑tuned Llama2 and Mistral content.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S5.0 GB 6.6 GB
Fits Get file →
IQ1_M5.5 GB 7.1 GB
Fits Get file →
IQ2_XXS6.4 GB 8.0 GB
Tight Get file →
IQ2_XS7.1 GB 8.7 GB
Too big Get file →
IQ2_S7.3 GB 8.9 GB
Too big Get file →
IQ2_M8.0 GB 9.6 GB
Too big Get file →
Q2_K8.8 GB 10.4 GB
Too big Get file →
IQ3_XXS9.3 GB 10.9 GB
Too big Get file →
IQ3_XS9.9 GB 11.5 GB
Too big Get file →
Q3_K_S10.4 GB 12.0 GB
Too big Get file →
IQ3_S10.5 GB 12.0 GB
Too big Get file →
IQ3_M10.6 GB 12.2 GB
Too big Get file →
Q3_K_M11.6 GB 13.2 GB
Too big Get file →
Q3_K_L12.5 GB 14.1 GB
Too big Get file →
IQ4_XS12.9 GB 14.5 GB
Too big Get file →
Q4_013.7 GB 15.3 GB
Too big Get file →
Q4_K_S13.7 GB 15.3 GB
Too big Get file →
Q4_K_M14.6 GB 16.2 GB
Too big Get file →
Q5_K_S16.6 GB 18.2 GB
Too big Get file →
Q5_K_M17.1 GB 18.7 GB
Too big Get file →
Q6_K19.8 GB 21.4 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (5.01 GB) or IQ1_M (5.53 GB). For 12 GB VRAM, IQ2_S (7.3 GB) or Q2_K (8.84 GB) are suitable. For 24 GB VRAM, Q5_K_M (17.13 GB) or Q6_K (19.82 GB) provide higher quality. Memory estimates are approximate.

What GPU do you need for aegolius acadicus 24b v2 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: the best quant that fits is IQ2_XXS (6.4 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ3_S (10.5 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (13.7 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (19.8 GB file, about 21.4 GB in use).

Which aegolius acadicus 24b v2 i1 quant should you choose?

Q4_K_M is the usual starting point for aegolius acadicus 24b v2 i1: it balances file size and quality well. Here it is a 14.6 GB file.

If memory is tight, the smallest file is IQ1_S at 5.0 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
Parameters24.2B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyAegolius
Licenseapache-2.0
Downloads (HF)1,688
Last updated2024-05-06

Frequently asked questions about aegolius acadicus 24b v2 i1

How much VRAM does aegolius acadicus 24b v2 i1 need?

About 16.2 GB at Q4_K_M with an 8K context window. That is the 14.6 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 aegolius acadicus 24b v2 i1 on an 8 GB GPU?

Yes, with IQ2_XXS: the 6.4 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of aegolius acadicus 24b v2 i1 GGUF?

It depends on the quant: IQ1_S is 5.0 GB, IQ1_M is 5.5 GB, IQ2_XXS is 6.4 GB, IQ2_XS is 7.1 GB, IQ2_S is 7.3 GB, IQ2_M is 8.0 GB and 15 more.

What context length does aegolius acadicus 24b v2 i1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download aegolius acadicus 24b v2 i1 GGUF?

The files are on Hugging Face in the mradermacher/aegolius-acadicus-24b-v2-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 aegolius acadicus 24b v2 i1 use?

Hugging Face lists the license as apache-2.0. 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 this model on 8 GB VRAM?

Yes, use the IQ1_S or IQ1_M quant, which are 5.01 GB and 5.53 GB respectively.

Does the model support languages other than English?

The model is trained primarily for English; no other languages are specified.

Is there a vision capability?

No, the model does not include vision support.

Other GGUFs of aegolius-acadicus-24b-v2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Aegolius models

All Aegolius →

Other medium models

All medium models →