LF

LFM2.5 230M heretic

LfmGGUF by saidutta69Updated 2026-10-28
Download on Hugging Face
Parameters230M
Context125K
Layers14
Architecturelfm2
Smallest quant0.1 GB
Quick answer

LFM2.5 230M heretic needs about 1.1 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.1 GB (Q2_K) to 0.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

LFM2.5 230M heretic – a compact, on‑device LLM for tool use and data extraction

LFM2.5 230M heretic is a 230M‑parameter, text‑only model built on the LFM2 architecture. It supports reasoning, roleplay, and tool use, and is optimized for low‑memory devices. The model runs with a 32,768‑token context window and is decensored for broader use.

Good at

  • Tool calling and function execution
  • Data extraction and structured output
  • Low‑memory inference on edge devices

Limits

  • Not suited for advanced math or creative writing
  • No vision support
  • Requires a quantized GGUF file for deployment

Best for

  • On‑device agentic pipelines
  • RAG on small hardware
  • Lightweight tool‑routing tasks

Who it’s for. Developers building lightweight, on‑device agents that need reliable tool use and data extraction. The model is ideal for environments where memory is limited and fast CPU inference is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.1 GB 1.1 GB
Fits Get file →
IQ3_S0.1 GB 1.1 GB
Fits Get file →
Q3_K_S0.1 GB 1.1 GB
Fits Get file →
Q3_K_M0.1 GB 1.1 GB
Fits Get file →
Q3_K_L0.1 GB 1.1 GB
Fits Get file →
IQ4_XS0.1 GB 1.1 GB
Fits Get file →
Q4_00.1 GB 1.1 GB
Fits Get file →
Q4_K_S0.1 GB 1.1 GB
Fits Get file →
Q4_K_M0.2 GB 1.1 GB
Fits Get file →
Q4_10.2 GB 1.1 GB
Fits Get file →
Q5_K_S0.2 GB 1.1 GB
Fits Get file →
Q5_K_M0.2 GB 1.1 GB
Fits Get file →
Q6_K0.2 GB 1.2 GB
Fits Get file →
Q8_00.2 GB 1.2 GB
Fits Get file →
F160.5 GB 1.4 GB
Fits Get file →

For 8 GB RAM, Q4_0 (0.15 GB) or Q4_K_M (0.15 GB) provide a good balance of speed and memory. If only 4 GB is available, choose Q4_K_S (0.15 GB) or Q4_K_M (0.15 GB). For the smallest footprint, Q2_K (0.12 GB) or IQ3_S (0.13 GB) fit under 1 GB and still run efficiently.

What GPU do you need for LFM2.5 230M 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: the best quant that fits is F16 (0.5 GB file, about 1.4 GB in use).

Which LFM2.5 230M heretic quant should you choose?

Q4_K_M is the usual starting point for LFM2.5 230M heretic: it balances file size and quality well. Here it is a 0.2 GB file.

The Q8_0 file is 0.2 GB, about 1.6 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 Q2_K at 0.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2
Parameters230M
Layers14
Trained context128,000 tokens
KV cache (fp16)56 KB per token

Source

Quantized bysaidutta69
FamilyLfm
Licenseother
Downloads (HF)1,192
Last updated2026-10-28

Frequently asked questions about LFM2.5 230M heretic

How much VRAM does LFM2.5 230M heretic need?

About 1.1 GB at Q4_K_M with an 8K context window. That is the 0.2 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 230M heretic on an 8 GB GPU?

Yes, with F16: the 0.5 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LFM2.5 230M heretic GGUF?

It depends on the quant: Q2_K is 0.1 GB, IQ3_S is 0.1 GB, Q3_K_S is 0.1 GB, Q3_K_M is 0.1 GB, Q3_K_L is 0.1 GB, IQ4_XS is 0.1 GB and 9 more.

What context length does LFM2.5 230M heretic support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download LFM2.5 230M heretic GGUF?

The files are on Hugging Face in the saidutta69/LFM2.5-230M-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 230M 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 230M heretic on a Raspberry Pi 5 with 4 GB RAM?

Yes, a Q4_K_S or Q4_K_M quant (~0.15 GB) will fit in RAM and run efficiently on a Raspberry Pi 5.

Does the model support vision or image input?

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

What context length does the model support?

The model supports a context length of 32,768 tokens.

Other GGUFs of LFM2.5-230M

Similar models

Browse all →

More from saidutta69

All by saidutta69 →

More Lfm models

All Lfm →

Other tiny models

All tiny models →