Skip to content
localllm
日本語

DavidAU

LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix

Parameters
24B
Max context length
131,072
Architecture
lfm2moe
License
Conditional
Base model
LiquidAI/LFM2.5-24B-A2B
License
lfm1.0
llama.cpp
b6709+

About LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix

LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix is a GGUF model based on LiquidAI/LFM2.5-24B-A2B on Hugging Face. GGUF files are published by DavidAU/LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix-GGUF. It has about 24B parameters, the lfm2moe architecture, a maximum context length of 131,072 tokens (values written in the GGUF).

There are 4 quantizations, with file sizes from 10.5 GB (IQ3_M) to 25.7 GB (Q8_0) (actual sizes on Hugging Face).

Running IQ3_M (10.5 GB) with an 8,192-token context needs an estimated 11.5 GB of memory, and an estimated 12.0 GB at 32,768 tokens. For 8,192 tokens, a GPU with 12 GB or more of VRAM (such as GeForce RTX 3080 Ti, GeForce RTX 5070), or a Mac with 12 GB or more of unified memory, is a rough guide (macOS caps how much memory the GPU can use, so leave some headroom).

The original model is licensed under LFM Open License v1.0, which allows commercial use with conditions such as scale or purpose. Check the original license for the terms of use.

File size and estimated memory per quantization

  • Up to 8 GB
  • Up to 16 GB
  • Up to 24 GB
  • Up to 48 GB
  • Up to 128 GB
  • More

File sizes are the actual values on Hugging Face. Memory is estimated for each context length (KV cache f16). The formula is in How memory is calculated.

All memory figures are Estimated (KV cache f16). It should run on a setup with at least this much VRAM (or Mac unified memory). Click a value to see the devices and models that fit that amount (Find by GPU / Mac).

About the "quality guide" (how far a quantization drifts from the original)

For each quantization type, how far the output drifts from the original model, grouped into six levels from values llama.cpp measured on Llama-3-8B.

The value is mean KLD (the difference between the original and quantized model in next-token probabilities); smaller means closer to the original. Quantizations made with an imatrix (importance data) come out slightly smaller. Levels use the value without an imatrix (or with one, for types that only have that).

These values were not measured on this model. Larger models and MoE models tend to drift less with the same type. Distributor-specific mixed types (such as UD-Q4_K_XL) cannot be matched by type name alone, so they show "-".

Quantization Quality guide KLD (no imatrix) KLD (imatrix) Size (Llama-3-8B)
Q8_0 Nearly identical 0.0014 - 7.96 GiB
Q6_K Very small 0.0055 - 6.14 GiB
Q5_K_M Very small 0.0108 - 5.33 GiB
Q5_K_S Small 0.0166 - 5.21 GiB
Q5_1 Small 0.0180 - 5.65 GiB
Q5_0 Small 0.0222 - 5.21 GiB
Q4_K_M Small 0.0313 0.0282 4.58 GiB
Q4_K_S Medium 0.0431 0.0320 4.37 GiB
IQ4_NL Small - 0.0357 4.35 GiB
IQ4_XS Small - 0.0363 4.14 GiB
Q4_1 Medium 0.0717 - 4.78 GiB
Q4_0 Medium 0.0719 - 4.34 GiB
Q3_K_L Medium 0.0872 0.0731 4.03 GiB
Q3_K_M Medium 0.1019 0.0844 3.74 GiB
IQ3_M Medium - 0.1025 3.53 GiB
IQ3_S Medium - 0.1113 3.42 GiB
IQ3_XS Large - 0.1387 3.28 GiB
IQ3_XXS Large - 0.1836 3.05 GiB
Q3_K_S Large 0.2282 0.1998 3.41 GiB
IQ2_M Large - 0.3260 2.74 GiB
Q2_K Very large 0.4451 0.3322 2.96 GiB
Q2_K_S Very large - 0.4034 2.96 GiB
IQ2_S Very large - 0.4392 2.56 GiB
IQ2_XS Very large - 0.5463 2.43 GiB
IQ2_XXS Very large - 0.8120 2.24 GiB
IQ1_M Very large - 1.3931 2.01 GiB
IQ1_S Very large - 2.2546 1.88 GiB

Source: llama.cpp (MIT), measured on Llama-3-8B against FP16, Wikitext-2, revision f364eb6f. Original table · Reading and choosing quantizations

GGUF source

DavidAU/LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix-GGUF

Published by the original developer About this label

Last checked: Nov 11, 2026

Architecture
lfm2moe
llama.cpp b6709 and later
Parameters
24.0B
Max context length
131,072
License
lfm1.0 Conditional
File size and memory per quantization for LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix (DavidAU/LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix-GGUF)
Quantization File size Measured Quality guide 4,096 8,192 16,384 32,768 65,536 131,072 max
IQ3_M 10.5 GB Medium 11.4 GB 11.5 GB 11.7 GB 12.0 GB 12.7 GB 14.0 GB
IQ4_XS 12.8 GB Small 13.7 GB 13.8 GB 14.0 GB 14.3 GB 15.0 GB 16.3 GB
Q6_K LFM2.5-24B-A2B-TBrill-NEO-Q6_K 19.7 GB Very small 20.6 GB 20.7 GB 20.8 GB 21.2 GB 21.8 GB 23.2 GB
Q6_K LFM2.5-24B-A2B-TBrill-MAX-NEO-Q6_K 20.0 GB Very small 20.9 GB 21.0 GB 21.1 GB 21.5 GB 22.1 GB 23.5 GB
Q8_0 25.7 GB Nearly identical 26.6 GB 26.7 GB 26.9 GB 27.2 GB 27.9 GB 29.2 GB 
Ollama  ollama run hf.co/DavidAU/LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix-GGUF:IQ3_M
llama.cpp  llama-server -hf DavidAU/LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix-GGUF:IQ3_M

License and commercial use

LFM Open License v1.0 Conditional

Commercial use by organizations with annual revenue of USD 10 million or more is not permitted under this license (a separate agreement is needed). Below that, commercial use is allowed.

Based on the license on the original model's Hugging Face page. Original license text (checked Oct 18, 2026)

The summary states facts this site read from the original text and is not legal advice. Always check the original license and its latest terms before use. All licenses

How to run

Mainline llama.cpp can load this model's format (lfm2moe) from b6709 (Oct 7, 2025) onward. Ollama and LM Studio bundle llama.cpp internally, so an older app fails to load it with errors such as "unknown model architecture". If that happens, update the app.

Example commands using IQ3_M. To use another quantization, replace the name with one from the table above. How to run local LLMs

Ollama

Run it by pointing directly at the GGUF on Hugging Face.

ollama run hf.co/DavidAU/LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix-GGUF:IQ3_M

llama.cpp

Pass the repository and quantization name to llama-server (or llama-cli) with -hf.

llama-server -hf DavidAU/LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix-GGUF:IQ3_M

LM Studio

Paste DavidAU/LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix-GGUF into the search box, download it, and choose the quantization from the file list.

Frequently asked questions

How much memory do I need to run LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix (IQ3_M)?
The file size is 10.5 GB (measured). With a 8,192-token context, the estimated memory including the KV cache is 11.5 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.
Can LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix be used commercially?
The original model's license is LFM Open License v1.0 (Commercial use with conditions).Commercial use by organizations with annual revenue of USD 10 million or more is not permitted under this license (a separate agreement is needed). Below that, commercial use is allowed. Check the original license text before deciding.
Does LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix run in 8 GB, 12 GB, 16 GB or 24 GB of VRAM?
8 GB: no quantization fits; 12 GB: up to IQ3_M (est. 11.5 GB); 16 GB: up to IQ4_XS (est. 13.8 GB); 24 GB: up to Q6_K (est. 21.0 GB) (estimated at 8,192 tokens with an f16 KV cache, files from the most-downloaded source).
What is the command to run LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix with Ollama?
Run "ollama run hf.co/DavidAU/LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix-GGUF:IQ3_M" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.