LFM2.5 2.6B Heretic NX PRIME 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 25 quants, from 0.0 GB to 2.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.
LFM2.5 2.6B Heretic NX PRIME – a 2.7B‑parameter LFM2 model
LFM2.5 2.6B Heretic NX PRIME is a behavioral edit of the LFM2.5 base model. It focuses on aggressive false‑refusal reduction while maintaining drift control. The model supports reasoning and tool usage.
Good at
- Reasoning tasks
- Tool‑based workflows
- False‑refusal mitigation
Limits
- No vision support
- Requires 131072 context tokens
- License is other
Best for
- Chatbot development
- Scripted tool integration
- Safety‑aware applications
Who it’s for. Developers building LLM‑powered assistants that need robust refusal handling and tool integration. The model is suitable for projects that can accommodate its 131072‑token context window and the specified license terms.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.5 GB | Fits | Get file → | |
| IQ1_S | 0.7 GB | 3.2 GB | Fits | Get file → | |
| IQ1_M | 0.7 GB | 3.2 GB | Fits | Get file → | |
| IQ2_XXS | 0.8 GB | 3.3 GB | Fits | Get file → | |
| IQ2_XS | 0.9 GB | 3.4 GB | Fits | Get file → | |
| IQ2_S | 0.9 GB | 3.4 GB | Fits | Get file → | |
| IQ2_M | 1.0 GB | 3.5 GB | Fits | Get file → | |
| Q2_K_S | 1.0 GB | 3.6 GB | Fits | Get file → | |
| Q2_K | 1.1 GB | 3.6 GB | Fits | Get file → | |
| IQ3_XXS | 1.1 GB | 3.6 GB | Fits | Get file → | |
| IQ3_XS | 1.2 GB | 3.7 GB | Fits | Get file → | |
| IQ3_S | 1.3 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_S | 1.3 GB | 3.8 GB | Fits | Get file → | |
| IQ3_M | 1.3 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_M | 1.4 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_L | 1.5 GB | 4.0 GB | Fits | Get file → | |
| IQ4_XS | 1.5 GB | 4.0 GB | Fits | Get file → | |
| IQ4_NL | 1.6 GB | 4.1 GB | Fits | Get file → | |
| Q4_0 | 1.6 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_S | 1.6 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_M | 1.7 GB | 4.2 GB | Fits | Get file → | |
| Q4_1 | 1.7 GB | 4.3 GB | Fits | Get file → | |
| Q5_K_S | 1.9 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_M | 1.9 GB | 4.5 GB | Fits | Get file → | |
| Q6_K | 2.2 GB | 4.7 GB | Fits | Get file → |
For 8 GB VRAM, use IQ1_S (0.68 GB, 3.2 GB memory at 8 k context) or IQ1_M (0.73 GB, 3.2 GB). With 12 GB VRAM, Q4_K_M (1.67 GB, 4.2 GB) or Q5_K_M (1.94 GB, 4.5 GB) are suitable. Larger VRAM allows Q6_K (2.22 GB, 4.7 GB).
What GPU do you need for LFM2.5 2.6B Heretic NX PRIME?
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 IQ4_XS (1.5 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (2.2 GB file, about 4.7 GB in use).
Which LFM2.5 2.6B Heretic NX PRIME quant should you choose?
Q4_K_M is the usual starting point for LFM2.5 2.6B Heretic NX PRIME: it balances file size and quality well. Here it is a 1.7 GB file.
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
Source
Frequently asked questions about LFM2.5 2.6B Heretic NX PRIME
How much VRAM does LFM2.5 2.6B Heretic NX PRIME 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 2.6B Heretic NX PRIME on an 8 GB GPU?
Yes, with Q6_K: the 2.2 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM2.5 2.6B Heretic NX PRIME GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 0.7 GB, IQ1_M is 0.7 GB, IQ2_XXS is 0.8 GB, IQ2_XS is 0.9 GB, IQ2_S is 0.9 GB and 19 more.
What context length does LFM2.5 2.6B Heretic NX PRIME support?
The GGUF header lists a trained context length of 131,072 tokens (128K). 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 2.6B Heretic NX PRIME GGUF?
The files are on Hugging Face in the mradermacher/LFM2.5-2.6B-Heretic-NX-PRIME-i1-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 2.6B Heretic NX PRIME 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 8 GB VRAM?
Yes, use IQ1_S or IQ1_M quant files, which require about 3.2 GB memory at 8 k context.
Does the model support vision?
No, the model has no vision capabilities.
What context length does it support?
It supports up to 131072 tokens.