LFM2.5 1.2B Instruct heretic needs about 2.3 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 0.0 GB to 1.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
LFM2.5 1.2B Instruct Heretic – a 1.2B parameter hybrid model for on‑device inference
LFM2.5 1.2B Instruct Heretic is a 1.17B parameter model built on a hybrid convolution + attention architecture. It is an abliterated version of LiquidAI/LFM2.5‑1.2B‑Instruct, removing safety refusals while preserving coherence. The model is available in multiple GGUF quantizations.
Good at
- Fast local inference
- Hybrid architecture for efficient token processing
- Uncensored instruction following
Limits
- No vision support
- Requires 8k context for memory estimates
- License is LFM Open License v1.0
Best for
- Research on alignment techniques
- Creative writing on-device
- Unrestricted local inference
Who it’s for. Researchers, developers, and content creators who need a fast, on‑device LLM that can comply with requests the original model refuses. Use responsibly and in accordance with applicable laws.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| IQ3_M | 0.6 GB | 2.1 GB | Fits | Get file → | |
| IQ4_XS | 0.7 GB | 2.2 GB | Fits | Get file → | |
| Q4_K_M | 0.7 GB | 2.3 GB | Fits | Get file → | |
| Q5_K_M | 0.8 GB | 2.4 GB | Fits | Get file → | |
| Q6_K | 1.0 GB | 2.5 GB | Fits | Get file → | |
| Q8_0 | 1.2 GB | 2.8 GB | Fits | Get file → |
For 8 GB VRAM, use IQ3_M (0.57 GB) or IQ4_XS (0.66 GB). For 4 GB VRAM, IQ3_M is recommended. For higher quality, Q4_K_M (0.73 GB) or Q5_K_M (0.84 GB) fit within 8 GB VRAM. Memory estimates are approximate.
What GPU do you need for LFM2.5 1.2B Instruct 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 Q8_0 (1.2 GB file, about 2.8 GB in use).
Which LFM2.5 1.2B Instruct heretic quant should you choose?
Q4_K_M is the usual starting point for LFM2.5 1.2B Instruct heretic: it balances file size and quality well. Here it is a 0.7 GB file.
The Q8_0 file is 1.2 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about LFM2.5 1.2B Instruct heretic
How much VRAM does LFM2.5 1.2B Instruct heretic need?
About 2.3 GB at Q4_K_M with an 8K context window. That is the 0.7 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 1.2B Instruct heretic on an 8 GB GPU?
Yes, with Q8_0: the 1.2 GB file needs about 2.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM2.5 1.2B Instruct heretic GGUF?
It depends on the quant: file is 0.0 GB, IQ3_M is 0.6 GB, IQ4_XS is 0.7 GB, Q4_K_M is 0.7 GB, Q5_K_M is 0.8 GB, Q6_K is 1.0 GB and 1 more.
What context length does LFM2.5 1.2B Instruct 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 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download LFM2.5 1.2B Instruct heretic GGUF?
The files are on Hugging Face in the richardyoung/LFM2.5-1.2B-Instruct-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 1.2B Instruct 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 this model on 4 GB VRAM?
Yes, the IQ3_M quantization is 0.57 GB and fits within 4 GB VRAM.
Does this model support vision tasks?
No, it has no vision capability.
What is the context length supported?
The model was trained with 128000 tokens and supports up to that context length.