LFM2 8B A1B Absolute Heresy MPOA needs about 7.2 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 6.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
LFM2 8B A1B Absolute Heresy MPOA – a small‑size MoE model for edge AI
LFM2 8B A1B Absolute Heresy MPOA is a mixture‑of‑experts model with 8.34 billion total parameters and 1 billion active parameters. It is designed for on‑device deployment and supports tool usage. The model was trained with a context length of 128 000 tokens.
Good at
- Tool‑enabled agentic tasks
- Data extraction and RAG
- Creative writing
Limits
- No vision support
- Requires Transformers v5.0.0 or higher
- License is other
Best for
- Edge AI agents
- Narrow fine‑tuning for specific domains
- Multi‑turn conversations
Who it’s for. Developers building lightweight on‑device agents who need a mixture‑of‑experts model with tool support. The model is suitable for mobile, tablet, and laptop deployments where memory is limited.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.1 GB | Fits | Get file → | |
| IQ1_S | 1.7 GB | 3.8 GB | Fits | Get file → | |
| IQ1_M | 1.9 GB | 4.0 GB | Fits | Get file → | |
| IQ2_XXS | 2.2 GB | 4.3 GB | Fits | Get file → | |
| IQ2_XS | 2.5 GB | 4.6 GB | Fits | Get file → | |
| IQ2_S | 2.5 GB | 4.6 GB | Fits | Get file → | |
| IQ2_M | 2.7 GB | 4.9 GB | Fits | Get file → | |
| Q2_K_S | 2.8 GB | 5.0 GB | Fits | Get file → | |
| Q2_K | 3.1 GB | 5.2 GB | Fits | Get file → | |
| IQ3_XXS | 3.2 GB | 5.4 GB | Fits | Get file → | |
| IQ3_XS | 3.4 GB | 5.6 GB | Fits | Get file → | |
| IQ3_S | 3.6 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_S | 3.6 GB | 5.8 GB | Fits | Get file → | |
| IQ3_M | 3.7 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_M | 4.0 GB | 6.1 GB | Fits | Get file → | |
| Q3_K_L | 4.3 GB | 6.4 GB | Fits | Get file → | |
| IQ4_XS | 4.5 GB | 6.6 GB | Fits | Get file → | |
| IQ4_NL | 4.7 GB | 6.8 GB | Fits | Get file → | |
| Q4_0 | 4.7 GB | 6.9 GB | Fits | Get file → | |
| Q4_K_S | 4.8 GB | 6.9 GB | Fits | Get file → | |
| Q4_K_M | 5.0 GB | 7.2 GB | Fits | Get file → | |
| Q4_1 | 5.2 GB | 7.4 GB | Tight | Get file → | |
| Q5_K_S | 5.8 GB | 7.9 GB | Tight | Get file → | |
| Q5_K_M | 5.9 GB | 8.0 GB | Too big | Get file → | |
| Q6_K | 6.8 GB | 9.0 GB | Too big | Get file → |
For 8 GB VRAM, Q4_K_M (5.04 GB file, 7.2 GB memory at 8 k context) is a good balance. For 4 GB VRAM, IQ1_S (1.73 GB file, 3.8 GB memory) or IQ1_M (1.92 GB file, 4 GB memory) are recommended. Smaller quants like IQ2_XXS (2.23 GB file, 4.3 GB memory) fit in 6 GB VRAM setups.
What GPU do you need for LFM2 8B A1B Absolute Heresy MPOA?
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 IQ1_M (1.9 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_M (3.7 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (5.9 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (6.8 GB file, about 9.0 GB in use).
Which LFM2 8B A1B Absolute Heresy MPOA quant should you choose?
Q4_K_M is the usual starting point for LFM2 8B A1B Absolute Heresy MPOA: it balances file size and quality well. Here it is a 5.0 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
Frequently asked questions about LFM2 8B A1B Absolute Heresy MPOA
How much VRAM does LFM2 8B A1B Absolute Heresy MPOA need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.0 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 8B A1B Absolute Heresy MPOA on an 8 GB GPU?
Yes, with Q5_K_M: the 5.9 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 8B A1B Absolute Heresy MPOA GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 1.7 GB, IQ1_M is 1.9 GB, IQ2_XXS is 2.2 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.5 GB and 19 more.
What context length does LFM2 8B A1B Absolute Heresy MPOA support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download LFM2 8B A1B Absolute Heresy MPOA GGUF?
The files are on Hugging Face in the mradermacher/LFM2-8B-A1B-absolute-heresy-MPOA-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 8B A1B Absolute Heresy MPOA 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 8B A1B on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 7.2 GB of VRAM at 8 k context, fitting within an 8 GB budget.
Does this model support vision tasks?
No, the model has no vision capability.
What is the recommended quant for a 4 GB VRAM device?
Use IQ1_S or IQ1_M, which use 3.8 GB or 4 GB of VRAM at 8 k context.