LF

LFM2.5 VL 450M heretic

LfmGGUF by saidutta69Updated 2026-10-28
Download on Hugging Face
Parameters354M
Context125K
Layers16
Architecturelfm2
Smallest quant0.2 GB
Quick answer

LFM2.5 VL 450M heretic needs about 1.3 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 0.2 GB (Q2_K) to 0.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.

LFM2.5 VL 450M heretic – a multimodal hybrid model for text and vision

LFM2.5 VL 450M heretic is a decensored variant of LiquidAI/LFM2.5-VL-450M. It retains the hybrid conv+attention backbone and includes a vision tower. The model is available in multiple GGUF quantizations and supports function calling.

Good at

  • Multimodal text and image tasks
  • Tool‑calling with ChatML format
  • Low‑memory inference on edge devices

Limits

  • Requires both main GGUF and projector GGUF for vision
  • No knowledge‑intensive tasks or programming
  • License type is other

Best for

  • Image captioning and visual question answering
  • Multilingual chat with function calls
  • Edge inference with limited VRAM

Who it’s for. Developers building multimodal applications on devices with limited memory. The model is suitable for projects that need both vision and text understanding without heavy GPU resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.2 GB 1.2 GB
Fits Get file →
IQ3_S0.2 GB 1.2 GB
Fits Get file →
Q3_K_S0.2 GB 1.2 GB
Fits Get file →
Q3_K_M0.2 GB 1.2 GB
Fits Get file →
Q3_K_L0.2 GB 1.2 GB
Fits Get file →
IQ4_XS0.2 GB 1.2 GB
Fits Get file →
Q4_00.2 GB 1.3 GB
Fits Get file →
Q4_K_S0.2 GB 1.3 GB
Fits Get file →
Q4_K_M0.2 GB 1.3 GB
Fits Get file →
Q4_10.2 GB 1.3 GB
Fits Get file →
Q5_K_S0.3 GB 1.3 GB
Fits Get file →
Q5_K_M0.3 GB 1.3 GB
Fits Get file →
Q6_K0.3 GB 1.3 GB
Fits Get file →
Q8_00.4 GB 1.4 GB
Fits Get file →
F160.7 GB 1.7 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M (0.23 GB) or Q5_K_M (0.26 GB) are recommended, giving about 1.3 GB memory usage at 8 k context. If 4 GB VRAM is available, Q3_K_M (0.19 GB) or Q3_K_S (0.18 GB) provide a good balance. The full precision F16 (0.71 GB) offers the best quality but requires more memory.

What GPU do you need for LFM2.5 VL 450M 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 (0.7 GB file, about 1.7 GB in use).

Which LFM2.5 VL 450M heretic quant should you choose?

Q4_K_M is the usual starting point for LFM2.5 VL 450M heretic: it balances file size and quality well. Here it is a 0.2 GB file.

The Q8_0 file is 0.4 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 Q2_K at 0.2 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
Parameters354M
Layers16
Trained context128,000 tokens
KV cache (fp16)64 KB per token

Source

Quantized bysaidutta69
FamilyLfm
Licenseother
Downloads (HF)1,144
Last updated2026-10-28

Frequently asked questions about LFM2.5 VL 450M heretic

How much VRAM does LFM2.5 VL 450M heretic need?

About 1.3 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 VL 450M heretic on an 8 GB GPU?

Yes, with F16: the 0.7 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LFM2.5 VL 450M heretic GGUF?

It depends on the quant: Q2_K is 0.2 GB, IQ3_S is 0.2 GB, Q3_K_S is 0.2 GB, Q3_K_M is 0.2 GB, Q3_K_L is 0.2 GB, IQ4_XS is 0.2 GB and 9 more.

What context length does LFM2.5 VL 450M 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 2.1 GB at 32K.

Where can I download LFM2.5 VL 450M heretic GGUF?

The files are on Hugging Face in the saidutta69/LFM2.5-VL-450M-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 VL 450M 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 450M heretic on 8 GB VRAM?

Yes, using Q4_K_M or Q5_K_M quantizations will keep memory usage around 1.3 GB at 8 k context.

Do I need the projector GGUF for image input?

Yes, both the main GGUF and the projector GGUF must be loaded for vision tasks.

Is the model suitable for programming tasks?

No, it is not recommended for knowledge‑intensive tasks or programming.

Other GGUFs of LFM2.5-350M

Similar models

Browse all →

More from saidutta69

All by saidutta69 →

More Lfm models

All Lfm →

Other tiny models

All tiny models →