LF

LFM2.5 8B A1B TAP DPQ 2.72bpw

LfmGGUF by DuoNeuralUpdated 2026-09-28
Download on Hugging Face
Parameters8.47B
Context125K
Layers24
Architecturelfm2moe
Smallest quant2.9 GB
Quick answer

LFM2.5 8B A1B TAP DPQ 2.72bpw needs about 5.0 GB of memory at its main file (a 2.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

LFM2.5 8B A1B TAP DPQ 2.72bpw – a hybrid reasoning model with MoE

LFM2.5 8B A1B TAP DPQ 2.72bpw is a 8.47B parameter model built on the lfm2moe architecture. It includes 24 layers, 6 full‑attention layers, and 18 convolutional/Mamba MoE layers with 32 experts. The model is trained on 128000 context tokens and licensed under apache‑2.0.

Good at

  • reasoning
  • tools usage
  • chain‑of‑thought generation

Limits

  • no vision support
  • requires 5 GB VRAM at 8k context
  • no other quantizations available

Best for

  • chatting with reasoning prompts
  • tool‑enabled workflows
  • long‑form text generation

Who it’s for. Developers and researchers needing a reasoning‑focused LLM with MoE capabilities. The model is suitable for applications that require detailed chain‑of‑thought reasoning and tool integration.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—2.9 GB 5.0 GB
Fits Get file →

The only available quant is unknown, 2.89 GB. It requires approximately 5 GB VRAM at 8k context. For lower memory budgets, no alternative quant is provided.

What GPU do you need for LFM2.5 8B A1B TAP DPQ 2.72bpw?

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: the best quant that fits is the main file (2.9 GB file, about 5.0 GB in use).

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 byDuoNeural
FamilyLfm
Licenseapache-2.0
Downloads (HF)125
Last updated2026-09-28

Frequently asked questions about LFM2.5 8B A1B TAP DPQ 2.72bpw

How much VRAM does LFM2.5 8B A1B TAP DPQ 2.72bpw need?

About 5.0 GB at its main file with an 8K context window. That is the 2.9 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 TAP DPQ 2.72bpw on an 8 GB GPU?

Yes, with the smaller files: the 2.9 GB file needs about 5.0 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 TAP DPQ 2.72bpw GGUF?

It depends on the quant: file is 2.9 GB.

What context length does LFM2.5 8B A1B TAP DPQ 2.72bpw 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 TAP DPQ 2.72bpw GGUF?

The files are on Hugging Face in the DuoNeural/LFM2.5-8B-A1B-TAP-DPQ-2.72bpw-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 TAP DPQ 2.72bpw 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, the model needs about 5 GB VRAM at 8k context, so 8 GB is sufficient.

Does this model support vision tasks?

No, the model has no vision capabilities.

What license does it use?

The model is released under the apache‑2.0 license.

Other GGUFs of LFM2.5-8B-A1B-Abliterated

Similar models

Browse all →

More from DuoNeural

All by DuoNeural →

More Lfm models

All Lfm →

Other small models

All small models →