LFM2.5 350M 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 350M heretic – a fast, uncensored, 350M‑parameter text‑only model
LFM2.5 350M heretic is a 350M‑parameter hybrid conv+attention model designed for on‑device inference. It supports reasoning, roleplay, and tool use, and runs under 1 GB of memory on a CPU or low‑end GPU.
Good at
- Reasoning and structured output
- Tool calling and function execution
- Multilingual text generation
Limits
- No vision support
- Not suited for knowledge‑intensive tasks
- No official license details
Best for
- Data extraction on edge devices
- Tool‑routing workflows
- RAG on low‑memory hardware
Who it’s for. Developers who need an uncensored assistant that runs fast on phones, Raspberry Pi, or browsers. Ideal for data extraction, structured output, and tool routing on hardware where larger models cannot fit.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.2 GB | 1.2 GB | Fits | Get file → | |
| IQ3_S | 0.2 GB | 1.2 GB | Fits | Get file → | |
| Q3_K_S | 0.2 GB | 1.2 GB | Fits | Get file → | |
| Q3_K_M | 0.2 GB | 1.2 GB | Fits | Get file → | |
| Q3_K_L | 0.2 GB | 1.2 GB | Fits | Get file → | |
| IQ4_XS | 0.2 GB | 1.2 GB | Fits | Get file → | |
| Q4_0 | 0.2 GB | 1.3 GB | Fits | Get file → | |
| Q4_K_S | 0.2 GB | 1.3 GB | Fits | Get file → | |
| Q4_K_M | 0.2 GB | 1.3 GB | Fits | Get file → | |
| Q4_1 | 0.2 GB | 1.3 GB | Fits | Get file → | |
| Q5_K_S | 0.3 GB | 1.3 GB | Fits | Get file → | |
| Q5_K_M | 0.3 GB | 1.3 GB | Fits | Get file → | |
| Q6_K | 0.3 GB | 1.3 GB | Fits | Get file → | |
| Q8_0 | 0.4 GB | 1.4 GB | Fits | Get file → | |
| F16 | 0.7 GB | 1.7 GB | Fits | Get file → |
For 8 GB RAM, use Q4_0 (0.22 GB file, ~1.3 GB memory at 8k context). For 4 GB RAM, choose Q3_K_M (0.19 GB file, ~1.2 GB memory). For 2 GB RAM, Q2_K (0.16 GB file, ~1.2 GB memory). Estimates are approximate.
What GPU do you need for LFM2.5 350M 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 350M heretic quant should you choose?
Q4_K_M is the usual starting point for LFM2.5 350M 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
Source
Frequently asked questions about LFM2.5 350M heretic
How much VRAM does LFM2.5 350M 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 350M 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 350M 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 350M 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 350M heretic GGUF?
The files are on Hugging Face in the saidutta69/LFM2.5-350M-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 350M 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 350M heretic on 4 GB VRAM?
Yes, using Q3_K_M or Q2_K quantizations keeps memory below 4 GB, but performance depends on CPU or GPU bandwidth.
Does this model support image inputs?
No, it is a text‑only model with no vision capabilities.
What is the maximum context length?
The model supports up to 32,768 tokens of context.