LF

LFM2.5 VL 3B Heretic

LfmGGUF by AX1Y2JPUpdated 2026-08-13
Download on Hugging Face
Parameters2.7B
Context125K
Layers30
Architecturelfm2
Smallest quant1.6 GB
Quick answer

LFM2.5 VL 3B 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 7 quants, from 1.6 GB (Q4_0) to 5.4 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

LFM2.5 VL 3B Heretic – multimodal LLM for on‑device vision and text

LFM2.5 VL 3B Heretic is a 2.7B parameter hybrid model that processes text and images. It uses the LFM2.5-2.6B language backbone and a SigLIP2 NaFlex vision encoder. The model supports a 32,768 token context and is optimized for low‑latency inference on edge devices.

Good at

  • High‑throughput vision‑text tasks
  • OCR with layout annotation
  • Real‑time object detection

Limits

  • No long‑context reasoning
  • Limited to 32,768 tokens
  • No vision support beyond images

Best for

  • Batch OCR of scanned documents
  • On‑device translation of menus
  • Near‑real‑time automotive object detection

Who it’s for. Developers building edge applications that require both text and image understanding. The model is suitable for mobile or embedded devices where memory and latency are critical.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_01.6 GB 4.1 GB
Fits Get file →
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 →
BF165.4 GB 7.9 GB
Tight Get file →
—5.4 GB 7.9 GB
Tight Get file →

For 8 GB VRAM, use Q4_0 (1.59 GB file, ~4.1 GB memory). For 12 GB VRAM, Q4_K_M (1.67 GB, ~4.2 GB) or Q5_K_M (1.94 GB, ~4.5 GB). For 16 GB VRAM, Q6_K (2.22 GB, ~4.7 GB) or Q8_0 (2.87 GB, ~5.4 GB).

What GPU do you need for LFM2.5 VL 3B 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 BF16 (5.4 GB file, about 7.9 GB in use).

Which LFM2.5 VL 3B Heretic quant should you choose?

Q4_K_M is the usual starting point for LFM2.5 VL 3B 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.

If memory is tight, the smallest file is Q4_0 at 1.6 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2
Parameters2.7B
Layers30
Trained context128,000 tokens
KV cache (fp16)240 KB per token

Source

Quantized byAX1Y2JP
FamilyLfm
Licenseother
Downloads (HF)1,116
Last updated2026-08-13

Frequently asked questions about LFM2.5 VL 3B Heretic

How much VRAM does LFM2.5 VL 3B 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 VL 3B Heretic on an 8 GB GPU?

Yes, with BF16: 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 VL 3B Heretic GGUF?

It depends on the quant: Q4_0 is 1.6 GB, 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, BF16 is 5.4 GB and 1 more.

What context length does LFM2.5 VL 3B 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 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download LFM2.5 VL 3B Heretic GGUF?

The files are on Hugging Face in the AX1Y2JP/LFM2.5-VL-3B-heretic-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 VL 3B 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 VL 3B Heretic on 8 GB VRAM?

Yes, the Q4_0 quantized model is 1.59 GB and requires about 4.1 GB of VRAM at 8 k context.

Does the model support image input?

Yes, it uses a SigLIP2 NaFlex vision encoder and can process images up to 512×512 patches.

What is the maximum context length?

The model supports 32,768 tokens of context.

Similar models

Browse all →

More from AX1Y2JP

All by AX1Y2JP →

More Lfm models

All Lfm →

Other tiny models

All tiny models →