LF

LFM2.5 8B A1B Opus Distil

LfmGGUF by TivaphraenUpdated 2026-06-11
Download on Hugging Face
Parameters8.47B
Context125K
Layers24
Architecturelfm2moe
Smallest quant4.1 GB
Quick answer

LFM2.5 8B A1B Opus Distil needs about 7.3 GB of memory at Q4_K_M (a 5.2 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 4.1 GB (Q3_K_M) to 9.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

LFM2.5 8B A1B Opus Distil – a reasoning‑focused Liquid Foundation Model

LFM2.5 8B A1B Opus Distil is a fine‑tuned Liquid Foundation Model with 8.47 billion parameters and 1 billion active parameters. It is trained on a reasoning dataset and produces structured, step‑by‑step responses. The model is released under Apache 2.0.

Good at

  • Reasoning with structured outputs
  • Markdown and LaTeX generation
  • Step‑by‑step explanations

Limits

  • No vision support
  • Large context requires high VRAM
  • Experimental research checkpoint

Best for

  • Chatbots needing reasoning steps
  • Educational content creation
  • Technical documentation generation

Who it’s for. Developers and researchers who need a lightweight reasoning model for English text generation. The model is suitable for experimentation and domain adaptation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M4.1 GB 6.2 GB
Fits Get file →
MXFP4_MOE4.9 GB 7.0 GB
Fits Get file →
Q4_K_M5.2 GB 7.3 GB
Tight Get file →
Q5_K_M6.0 GB 8.1 GB
Too big Get file →
Q6_K7.0 GB 9.1 GB
Too big Get file →
Q8_09.0 GB 11.1 GB
Too big Get file →

For 8 GB VRAM, use Q3_K_M (4.11 GB, 6.2 GB memory at 8 k context) or MXFP4_MOE (4.89 GB, 7 GB memory). For 12 GB VRAM, Q4_K_M (5.16 GB, 7.3 GB memory) or Q5_K_M (6.03 GB, 8.1 GB memory) are recommended. Larger VRAM allows Q6_K or Q8_0 for higher quality.

What GPU do you need for LFM2.5 8B A1B Opus Distil?

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 Q4_K_M (5.2 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.0 GB file, about 11.1 GB in use).

Which LFM2.5 8B A1B Opus Distil quant should you choose?

Q4_K_M is the usual starting point for LFM2.5 8B A1B Opus Distil: it balances file size and quality well. Here it is a 5.2 GB file.

The Q8_0 file is 9.0 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 Q3_K_M at 4.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2moe
Parameters8.47B (approximate, mixture of experts)
Active parameters1B
Layers24
Trained context128,000 tokens
KV cache (fp16)192 KB per token

Source

Quantized byTivaphraen
FamilyLfm
Licenseapache-2.0
Downloads (HF)530
Last updated2026-06-11

Frequently asked questions about LFM2.5 8B A1B Opus Distil

How much VRAM does LFM2.5 8B A1B Opus Distil need?

About 7.3 GB at Q4_K_M with an 8K context window. That is the 5.2 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 LFM2.5 8B A1B Opus Distil on an 8 GB GPU?

Yes, with Q4_K_M: the 5.2 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LFM2.5 8B A1B Opus Distil GGUF?

It depends on the quant: Q3_K_M is 4.1 GB, MXFP4_MOE is 4.9 GB, Q4_K_M is 5.2 GB, Q5_K_M is 6.0 GB, Q6_K is 7.0 GB, Q8_0 is 9.0 GB.

What context length does LFM2.5 8B A1B Opus Distil support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download LFM2.5 8B A1B Opus Distil GGUF?

The files are on Hugging Face in the Tivaphraen/LFM2.5-8B-A1B-Opus-Distil-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 LFM2.5 8B A1B Opus Distil 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 Q3_K_M or MXFP4_MOE quantizations; they fit within 8 GB VRAM with estimated memory usage of 6.2–7 GB at 8 k context.

Does the model support vision?

No, the model has no vision capabilities and is designed for text generation only.

What license applies to this model?

The model is released under the Apache 2.0 license, inherited from the parent model.

Other GGUFs of LFM2.5-8B-A1B-Opus-Distil

Similar models

Browse all →

More from Tivaphraen

All by Tivaphraen →

More Lfm models

All Lfm →

Other small models

All small models →