LFM2 VL 3B Heretic needs about 4.1 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 26 quants, from 0.6 GB (IQ1_S) to 5.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.
LFM2 VL 3B Heretic – multimodal LLM for text and image tasks
LFM2 VL 3B Heretic is a 2.57 billion‑parameter model that processes text and images. It supports native resolutions up to 512×512 and uses a patch‑based approach for larger inputs. The model is optimized for efficient inference and instruction following.
Good at
- Vision‑text reasoning
- Fine‑grained perception
- Instruction following
Limits
- No safety‑critical use
- Single‑language (English)
- No vision beyond 512×512 native resolution
Best for
- Multimodal chat assistants
- Image captioning
- Visual question answering
Who it’s for. Developers needing a lightweight multimodal model for English‑only applications. Suitable for fine‑tuning on narrow use cases to maximize performance.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.6 GB | 3.1 GB | Fits | Get file → | |
| IQ1_M | 0.6 GB | 3.2 GB | Fits | Get file → | |
| IQ2_XXS | 0.7 GB | 3.2 GB | Fits | Get file → | |
| IQ2_XS | 0.8 GB | 3.3 GB | Fits | Get file → | |
| IQ2_S | 0.8 GB | 3.3 GB | Fits | Get file → | |
| IQ2_M | 0.9 GB | 3.4 GB | Fits | Get file → | |
| Q2_K | 1.0 GB | 3.5 GB | Fits | Get file → | |
| IQ3_XXS | 1.0 GB | 3.5 GB | Fits | Get file → | |
| IQ3_XS | 1.1 GB | 3.6 GB | Fits | Get file → | |
| IQ3_S | 1.2 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_S | 1.2 GB | 3.7 GB | Fits | Get file → | |
| IQ3_M | 1.2 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_M | 1.3 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_L | 1.3 GB | 3.9 GB | Fits | Get file → | |
| IQ4_XS | 1.4 GB | 3.9 GB | Fits | Get file → | |
| IQ4_NL | 1.5 GB | 4.0 GB | Fits | Get file → | |
| Q4_0 | 1.5 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_S | 1.5 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_M | 1.6 GB | 4.1 GB | Fits | Get file → | |
| Q4_1 | 1.6 GB | 4.1 GB | Fits | Get file → | |
| Q5_K_S | 1.8 GB | 4.3 GB | Fits | Get file → | |
| Q5_0 | 1.8 GB | 4.3 GB | Fits | Get file → | |
| Q5_K_M | 1.8 GB | 4.3 GB | Fits | Get file → | |
| Q6_K | 2.1 GB | 4.6 GB | Fits | Get file → | |
| Q8_0 | 2.7 GB | 5.2 GB | Fits | Get file → | |
| F16 | 5.1 GB | 7.7 GB | Tight | Get file → |
For 8 GB VRAM, use IQ1_S (0.58 GB, 3.1 GB memory) or IQ1_M (0.64 GB, 3.2 GB memory). For 12 GB VRAM, Q4_K_M (1.56 GB, 4.1 GB memory) or Q5_K_M (1.83 GB, 4.3 GB memory) are good choices. Larger models like F16 require 5.14 GB and 7.7 GB memory, suitable for high‑end GPUs.
What GPU do you need for LFM2 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: the best quant that fits is Q4_K_S (1.5 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (2.7 GB file, about 5.2 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (5.1 GB file, about 7.7 GB in use).
Which LFM2 VL 3B Heretic quant should you choose?
Q4_K_M is the usual starting point for LFM2 VL 3B Heretic: it balances file size and quality well. Here it is a 1.6 GB file.
The Q8_0 file is 2.7 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 IQ1_S at 0.6 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
Source
Frequently asked questions about LFM2 VL 3B Heretic
How much VRAM does LFM2 VL 3B Heretic need?
About 4.1 GB at Q4_K_M with an 8K context window. That is the 1.6 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 VL 3B Heretic on an 8 GB GPU?
Yes, with F16: the 5.1 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM2 VL 3B Heretic GGUF?
It depends on the quant: IQ1_S is 0.6 GB, IQ1_M is 0.6 GB, IQ2_XXS is 0.7 GB, IQ2_XS is 0.8 GB, IQ2_S is 0.8 GB, IQ2_M is 0.9 GB and 20 more.
What context length does LFM2 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 VL 3B Heretic GGUF?
The files are on Hugging Face in the ZuzeTt/LFM2-VL-3B-heretic-Imatrix-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 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 VL 3B Heretic on 8 GB VRAM?
Yes, using IQ1_S or IQ1_M quantizations which use about 3.1–3.2 GB memory at 8k context.
Does the model support multiple languages?
No, it is trained for English only.
Is the model safe for critical decision making?
No, it is not intended for safety‑critical decisions.