LU

Luciole 23B Thinking 1.1

LucioleGGUF by OpenLLM-FranceUpdated 2026-09-09
Download on Hugging Face
Parameters23.2B
Context128K
Layers40
Architecturenemotron
Smallest quant14.5 GB
Quick answer

Luciole 23B Thinking 1.1 needs about 16.3 GB of memory at Q4_K_M (a 14.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 14.5 GB (Q4_K_M) to 46.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Luciole 23B Thinking 1.1 is a 23.2B-parameter Luciole model in GGUF format, quantized by OpenLLM-France. Its trained context length is 128K tokens. The repository has 4 quant files, from 14.5 GB (Q4_K_M) to 46.4 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M14.5 GB 16.3 GB
Too big Get file →
Q5_K_M16.7 GB 18.5 GB
Too big Get file →
Q8_024.7 GB 26.5 GB
Too big Get file →
BF1646.4 GB 48.3 GB
Too big Get file →

What GPU do you need for Luciole 23B Thinking 1.1?

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 Q5_K_M (16.7 GB file, about 18.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (24.7 GB file, about 26.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (24.7 GB file, about 26.5 GB in use).

Which Luciole 23B Thinking 1.1 quant should you choose?

Q4_K_M is the usual starting point for Luciole 23B Thinking 1.1: it balances file size and quality well. Here it is a 14.5 GB file.

The Q8_0 file is 24.7 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturenemotron
Parameters23.2B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized byOpenLLM-France
FamilyLuciole
Licenseapache-2.0
Downloads (HF)133
Last updated2026-09-09

Frequently asked questions about Luciole 23B Thinking 1.1

How much VRAM does Luciole 23B Thinking 1.1 need?

About 16.3 GB at Q4_K_M with an 8K context window. That is the 14.5 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 Luciole 23B Thinking 1.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Luciole 23B Thinking 1.1 GGUF?

It depends on the quant: Q4_K_M is 14.5 GB, Q5_K_M is 16.7 GB, Q8_0 is 24.7 GB, BF16 is 46.4 GB.

What context length does Luciole 23B Thinking 1.1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Luciole 23B Thinking 1.1 GGUF?

The files are on Hugging Face in the OpenLLM-France/Luciole-23B-Thinking-1.1-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 Luciole 23B Thinking 1.1 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.

Similar models

Browse all →

More from OpenLLM-France

All by OpenLLM-France →

More Luciole models

All Luciole →

Other medium models

All medium models →