LFM2 24B A2B Heretic Ara needs about 17.6 GB of memory at Q4_K_M (a 14.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.1 GB to 19.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
LFM2 24B A2B Heretic Ara – 24B MoE model with 2B active params
LFM2 24B A2B Heretic Ara is a 24.8B parameter hybrid model with 2B active parameters per token. It supports 128000 context tokens and is optimized for on‑device inference. The model is available in multiple GGUF quantizations.
Good at
- Tool‑based agent workflows
- Offline summarization and Q&A
- Privacy‑preserving customer support
Limits
- No vision support
- Requires large VRAM for higher‑quality quants
- License type is other
Best for
- Fast inner‑loop agent models
- On‑premise document analysis
- Multi‑turn support conversations
Who it’s for. Developers building privacy‑sensitive applications that need a large‑scale LLM on consumer hardware. The model is suitable for users who can run GGUF files with llama.cpp, vLLM, or SGLang.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 3.2 GB | Fits | Get file → | |
| IQ1_S | 4.8 GB | 8.0 GB | Too big | Get file → | |
| IQ1_M | 5.4 GB | 8.6 GB | Too big | Get file → | |
| IQ2_XXS | 6.3 GB | 9.5 GB | Too big | Get file → | |
| IQ2_XS | 7.0 GB | 10.2 GB | Too big | Get file → | |
| IQ2_S | 7.1 GB | 10.3 GB | Too big | Get file → | |
| IQ2_M | 7.8 GB | 11.0 GB | Too big | Get file → | |
| Q2_K_S | 8.1 GB | 11.2 GB | Too big | Get file → | |
| Q2_K | 8.7 GB | 11.9 GB | Too big | Get file → | |
| IQ3_XXS | 9.2 GB | 12.4 GB | Too big | Get file → | |
| IQ3_XS | 9.8 GB | 12.9 GB | Too big | Get file → | |
| IQ3_S | 10.3 GB | 13.5 GB | Too big | Get file → | |
| Q3_K_S | 10.3 GB | 13.5 GB | Too big | Get file → | |
| IQ3_M | 10.4 GB | 13.6 GB | Too big | Get file → | |
| Q3_K_M | 11.4 GB | 14.5 GB | Too big | Get file → | |
| Q3_K_L | 12.3 GB | 15.5 GB | Too big | Get file → | |
| IQ4_XS | 12.7 GB | 15.9 GB | Too big | Get file → | |
| Q4_0 | 13.5 GB | 16.7 GB | Too big | Get file → | |
| Q4_K_S | 13.5 GB | 16.7 GB | Too big | Get file → | |
| Q4_K_M | 14.4 GB | 17.6 GB | Too big | Get file → | |
| Q4_1 | 14.9 GB | 18.1 GB | Too big | Get file → | |
| Q5_K_S | 16.4 GB | 19.6 GB | Too big | Get file → | |
| Q5_K_M | 16.9 GB | 20.1 GB | Too big | Get file → | |
| Q6_K | 19.6 GB | 22.8 GB | Too big | Get file → |
For 8 GB VRAM use IQ1_S (file size 4.84 GB, memory 8 GB at 8k context). For 12 GB VRAM use IQ1_M (5.38 GB, 8.6 GB). For 16 GB VRAM use Q2_XS (7 GB, 10.2 GB). Larger quants require more memory.
What GPU do you need for LFM2 24B A2B Heretic Ara?
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 the main file (0.1 GB file, about 3.2 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 3.2 GB in use).
- 8 GB VRAM: the best quant that fits is IQ1_S (4.8 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q2_K (8.7 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is IQ4_XS (12.7 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (19.6 GB file, about 22.8 GB in use).
Which LFM2 24B A2B Heretic Ara quant should you choose?
Q4_K_M is the usual starting point for LFM2 24B A2B Heretic Ara: it balances file size and quality well. Here it is a 14.4 GB file.
If memory is tight, the smallest file is the first one in the table at 0.1 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 24B A2B Heretic Ara
How much VRAM does LFM2 24B A2B Heretic Ara need?
About 17.6 GB at Q4_K_M with an 8K context window. That is the 14.4 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 24B A2B Heretic Ara on an 8 GB GPU?
Yes, with IQ1_S: the 4.8 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM2 24B A2B Heretic Ara GGUF?
It depends on the quant: file is 0.1 GB, IQ1_S is 4.8 GB, IQ1_M is 5.4 GB, IQ2_XXS is 6.3 GB, IQ2_XS is 7.0 GB, IQ2_S is 7.1 GB and 18 more.
What context length does LFM2 24B A2B Heretic Ara support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download LFM2 24B A2B Heretic Ara GGUF?
The files are on Hugging Face in the mradermacher/LFM2-24B-A2B-heretic-ara-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 24B A2B Heretic Ara 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 24B A2B Heretic Ara on 8 GB VRAM?
Yes, the IQ1_S quant uses 8 GB of VRAM at 8k context, which fits an 8 GB GPU.
Does the model support vision tasks?
No, the model has no vision capabilities.
What is the context length of this model?
The model was trained with 128000 context tokens.