LF

LFM2.5 2.6B heretic

LfmGGUF by atakankutalpUpdated 2026-09-26
Download on Hugging Face
Parameters2.7B
Context128K
Layers30
Architecturelfm2
Smallest quant1.7 GB
Quick answer

LFM2.5 2.6B heretic needs about 4.2 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 1.7 GB (Q4_K_M) to 5.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

LFM2.5 2.6B heretic – a 2.7B‑parameter hybrid LFM model with 128K context

LFM2.5 2.6B heretic is a 2.7B‑parameter text‑only model based on the LFM2 architecture. It supports a 131072‑token context window and is optimized for on‑device inference. The model is a directional ablation of LiquidAI/LFM2.5‑2.6B with reduced safety alignment.

Good at

  • Long‑context reasoning
  • Agentic tool use
  • Data extraction

Limits

  • No vision support
  • Safety alignment reduced
  • No coding agentic tasks

Best for

  • RAG pipelines
  • Multi‑step agentic workflows
  • Tool‑enabled data extraction

Who it’s for. Developers building lightweight, on‑device LLMs that need large context and agentic capabilities. Suitable for research and production environments where memory is limited and safety filtering is not required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.7 GB 4.2 GB
Fits Get file →
Q5_K_M1.9 GB 4.5 GB
Fits Get file →
Q6_K2.2 GB 4.7 GB
Fits Get file →
Q8_02.9 GB 5.4 GB
Fits Get file →
F165.4 GB 7.9 GB
Tight Get file →

For 8 GB VRAM, use Q4_K_M (1.67 GB, ~4.2 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (1.94 GB, ~4.5 GB). For 16 GB VRAM, Q6_K (2.22 GB, ~4.7 GB). Higher precision quants increase memory usage.

What GPU do you need for LFM2.5 2.6B heretic?

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 Q8_0 (2.9 GB file, about 5.4 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (5.4 GB file, about 7.9 GB in use).

Which LFM2.5 2.6B heretic quant should you choose?

Q4_K_M is the usual starting point for LFM2.5 2.6B heretic: it balances file size and quality well. Here it is a 1.7 GB file.

The Q8_0 file is 2.9 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

Architecturelfm2
Parameters2.7B
Layers30
Trained context131,072 tokens
KV cache (fp16)240 KB per token

Source

Quantized byatakankutalp
FamilyLfm
Licenseother
Downloads (HF)464
Last updated2026-09-26

Frequently asked questions about LFM2.5 2.6B heretic

How much VRAM does LFM2.5 2.6B heretic need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 1.7 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 2.6B heretic on an 8 GB GPU?

Yes, with F16: the 5.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LFM2.5 2.6B heretic GGUF?

It depends on the quant: Q4_K_M is 1.7 GB, Q5_K_M is 1.9 GB, Q6_K is 2.2 GB, Q8_0 is 2.9 GB, F16 is 5.4 GB.

What context length does LFM2.5 2.6B heretic support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download LFM2.5 2.6B heretic GGUF?

The files are on Hugging Face in the atakankutalp/LFM2.5-2.6B-heretic 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 2.6B heretic use?

Hugging Face lists the license as other. 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 LFM2.5 2.6B heretic on 8 GB VRAM?

Yes, using the Q4_K_M quantized file (1.67 GB) will fit within 8 GB VRAM with an estimated 4.2 GB memory usage at 8k context.

Does this model support vision tasks?

No, the model is text‑only and does not include vision capabilities.

What is the context length of this model?

The model supports a context length of 131072 tokens.

Other GGUFs of LFM2.5-2.6B

Similar models

Browse all →

More from atakankutalp

All by atakankutalp →

More Lfm models

All Lfm →

Other tiny models

All tiny models →