LFM2 24B A2B REAP needs about 10.7 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 10.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
LFM2 24B A2B REAP – a 12.4B parameter LFM2 mixture of experts model
LFM2 24B A2B REAP is a 12.4B parameter LFM2 model with 2B active parameters. It supports a context length of 128000 tokens and is available in multiple GGUF quantizations. The model is released under an other license.
Good at
- Large context handling
- Mixture of experts efficiency
- Multiple quantization options
Limits
- No vision support
- Requires 8k context for memory estimates
- License not specified
Best for
- Long-form text generation
- Context‑heavy dialogue
- Research prototyping
Who it’s for. Developers and researchers who need a large‑context LFM2 model with flexible quantization. The model is suitable for local deployment using llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 3.2 GB | Fits | Get file → | |
| IQ1_S | 2.5 GB | 5.7 GB | Fits | Get file → | |
| IQ1_M | 2.8 GB | 6.0 GB | Fits | Get file → | |
| IQ2_XXS | 3.3 GB | 6.5 GB | Fits | Get file → | |
| IQ2_XS | 3.7 GB | 6.8 GB | Fits | Get file → | |
| IQ2_S | 3.7 GB | 6.9 GB | Fits | Get file → | |
| IQ2_M | 4.1 GB | 7.3 GB | Tight | Get file → | |
| Q2_K_S | 4.2 GB | 7.4 GB | Tight | Get file → | |
| Q2_K | 4.5 GB | 7.7 GB | Tight | Get file → | |
| IQ3_XXS | 4.8 GB | 8.0 GB | Tight | Get file → | |
| IQ3_XS | 5.1 GB | 8.3 GB | Too big | Get file → | |
| IQ3_S | 5.4 GB | 8.6 GB | Too big | Get file → | |
| Q3_K_S | 5.4 GB | 8.6 GB | Too big | Get file → | |
| IQ3_M | 5.4 GB | 8.6 GB | Too big | Get file → | |
| Q3_K_M | 5.9 GB | 9.1 GB | Too big | Get file → | |
| Q3_K_L | 6.4 GB | 9.6 GB | Too big | Get file → | |
| IQ4_XS | 6.6 GB | 9.8 GB | Too big | Get file → | |
| IQ4_NL | 7.0 GB | 10.2 GB | Too big | Get file → | |
| Q4_0 | 7.0 GB | 10.2 GB | Too big | Get file → | |
| Q4_K_S | 7.0 GB | 10.2 GB | Too big | Get file → | |
| Q4_K_M | 7.5 GB | 10.7 GB | Too big | Get file → | |
| Q4_1 | 7.8 GB | 11.0 GB | Too big | Get file → | |
| Q5_K_S | 8.5 GB | 11.7 GB | Too big | Get file → | |
| Q5_K_M | 8.8 GB | 12.0 GB | Too big | Get file → | |
| Q6_K | 10.2 GB | 13.3 GB | Too big | Get file → |
For 8GB VRAM, use IQ1_S (5.7GB) or IQ1_M (6GB). If 12GB VRAM is available, Q3_K_M (9.1GB) or Q4_K_M (10.7GB) provide a good balance of size and performance. Larger models such as Q6_K (13.3GB) require more memory.
What GPU do you need for LFM2 24B A2B REAP?
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 (0.0 GB file, about 3.2 GB in use).
- 6 GB VRAM: the best quant that fits is IQ1_M (2.8 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_XXS (4.8 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_M (8.8 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (10.2 GB file, about 13.3 GB in use).
Which LFM2 24B A2B REAP quant should you choose?
Q4_K_M is the usual starting point for LFM2 24B A2B REAP: it balances file size and quality well. Here it is a 7.5 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 24B A2B REAP
How much VRAM does LFM2 24B A2B REAP need?
About 10.7 GB at Q4_K_M with an 8K context window. That is the 7.5 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 REAP on an 8 GB GPU?
Yes, with IQ3_XXS: 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 REAP GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 2.5 GB, IQ1_M is 2.8 GB, IQ2_XXS is 3.3 GB, IQ2_XS is 3.7 GB, IQ2_S is 3.7 GB and 19 more.
What context length does LFM2 24B A2B REAP 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 REAP GGUF?
The files are on Hugging Face in the mradermacher/LFM2-24B-A2B-REAP-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 REAP 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 REAP on 8 GB VRAM?
Yes, with the IQ1_S or IQ1_M quantizations, which use about 5.7GB or 6GB at 8k context.
Does the model support vision tasks?
No, the model has no vision capabilities.
What context length does the model support?
The model was trained with a context length of 128000 tokens.