LE

LeEmpereur

LeempereurGGUF by mradermacherUpdated 2024-09-19
Download on Hugging Face
Parameters2.23B
Context32K
Layers9
Architecturellama
Smallest quant0.9 GB
Quick answer

LeEmpereur needs about 2.2 GB of memory at Q4_K_M (a 1.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.9 GB (Q2_K) to 4.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.

LeEmpereur – a 2.23B llama model in GGUF format

LeEmpereur is a 2.23B parameter llama model quantized into multiple GGUF files. It supports a 32768 token context window and is available in a range of quantizations from Q2_K to F16. The model is provided by mradermacher and can be used with llama.cpp.

Good at

  • Large context handling
  • Low memory variants
  • Versatile quant options

Limits

  • No license information provided
  • No vision capabilities
  • No mixture of experts

Best for

  • Chatbots with long context
  • Fine‑tuning on limited GPU
  • Educational demos

Who it’s for. Developers and researchers needing a compact llama model with extensive context support. The model is suitable for those who can manage the required VRAM and prefer a variety of quantization options.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.9 GB 1.7 GB
Fits Get file →
IQ3_XS1.0 GB 1.8 GB
Fits Get file →
Q3_K_S1.0 GB 1.8 GB
Fits Get file →
IQ3_S1.0 GB 1.8 GB
Fits Get file →
IQ3_M1.0 GB 1.8 GB
Fits Get file →
Q3_K_M1.1 GB 1.9 GB
Fits Get file →
Q3_K_L1.2 GB 2.0 GB
Fits Get file →
IQ4_XS1.2 GB 2.0 GB
Fits Get file →
Q4_K_S1.3 GB 2.1 GB
Fits Get file →
Q4_K_M1.4 GB 2.2 GB
Fits Get file →
Q5_K_S1.5 GB 2.4 GB
Fits Get file →
Q5_K_M1.6 GB 2.4 GB
Fits Get file →
Q6_K1.8 GB 2.6 GB
Fits Get file →
Q8_02.4 GB 3.2 GB
Fits Get file →
F164.5 GB 5.3 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (est. 2.2 GB) or Q5_K_S (est. 2.4 GB). If 12 GB VRAM is available, Q6_K (est. 2.6 GB) or Q8_0 (est. 3.2 GB) provide higher quality. For 16 GB VRAM, the F16 quant (est. 5.3 GB) offers the best fidelity.

What GPU do you need for LeEmpereur?

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: the best quant that fits is Q8_0 (2.4 GB file, about 3.2 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (4.5 GB file, about 5.3 GB in use).

Which LeEmpereur quant should you choose?

Q4_K_M is the usual starting point for LeEmpereur: it balances file size and quality well. Here it is a 1.4 GB file.

The Q8_0 file is 2.4 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 0.9 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
Parameters2.23B
Layers9
Trained context32,768 tokens
KV cache (fp16)36 KB per token

Source

Quantized bymradermacher
Downloads (HF)799
Last updated2024-09-19

Frequently asked questions about LeEmpereur

How much VRAM does LeEmpereur need?

About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.4 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 LeEmpereur on an 8 GB GPU?

Yes, with F16: the 4.5 GB file needs about 5.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LeEmpereur GGUF?

It depends on the quant: Q2_K is 0.9 GB, IQ3_XS is 1.0 GB, Q3_K_S is 1.0 GB, IQ3_S is 1.0 GB, IQ3_M is 1.0 GB, Q3_K_M is 1.1 GB and 9 more.

What context length does LeEmpereur support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.

Where can I download LeEmpereur GGUF?

The files are on Hugging Face in the mradermacher/LeEmpereur-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run LeEmpereur on 8 GB VRAM?

Yes, use Q4_K_M or Q5_K_S quantizations, which estimate 2.2 GB or 2.4 GB of VRAM at 8k context.

Does LeEmpereur support vision tasks?

No, the model has no vision capabilities.

What is the maximum context length for LeEmpereur?

The model supports a 32768 token context window.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Leempereur models

All Leempereur →

Other tiny models

All tiny models →