LFM2.5 8B A1B APEX needs about 8.2 GB of memory at its main file (a 6.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 7 quants, from 3.6 GB to 6.3 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
LFM2.5 8B A1B APEX – a hybrid MoE model for on‑device text tasks
LFM2.5 8B A1B APEX is a text‑only Mixture‑of‑Experts model with 8.47B total parameters and 1B active parameters per token. It supports a 128,000 token context and is optimized for on‑device inference via APEX quantization.
Good at
- Agentic workflows
- Tool use
- Multilingual assistance
Limits
- No vision support
- Requires 8,000 token context for memory estimates
- License is other
Best for
- On‑device personal assistants
- Structured output generation
- Tool‑calling applications
Who it’s for. Developers building lightweight, on‑device assistants that need reasoning and multilingual support. The model is suitable for applications that can run with 8‑k context and do not require heavy programming or retrieval‑intensive Q&A.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 3.6 GB | 5.7 GB | Fits | Get file → | |
| — | 4.2 GB | 6.3 GB | Fits | Get file → | |
| — | 4.2 GB | 6.3 GB | Fits | Get file → | |
| — | 6.1 GB | 8.2 GB | Too big | Get file → | |
| — | 6.1 GB | 8.2 GB | Too big | Get file → | |
| — | 6.3 GB | 8.4 GB | Too big | Get file → | |
| — | 6.3 GB | 8.4 GB | Too big | Get file → |
The smallest APEX file is 3.64 GB and needs about 5.7 GB of VRAM at 8 k context. A 4.21 GB file uses roughly 6.3 GB. For tighter budgets use the 3.64 GB version; for higher performance use the 4.21 GB version. Memory estimates are approximate.
What GPU do you need for LFM2.5 8B A1B APEX?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is the main file (3.6 GB file, about 5.7 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (4.2 GB file, about 6.3 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (6.3 GB file, about 8.4 GB in use).
Which LFM2.5 8B A1B APEX quant should you choose?
If memory is tight, the smallest file is the first one in the table at 3.6 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 8B A1B APEX
How much VRAM does LFM2.5 8B A1B APEX need?
About 8.2 GB at its main file with an 8K context window. That is the 6.1 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 8B A1B APEX on an 8 GB GPU?
Yes, with the smaller files: the 4.2 GB file needs about 6.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM2.5 8B A1B APEX GGUF?
It depends on the quant: file is 3.6 GB, file is 4.2 GB, file is 4.2 GB, file is 6.1 GB, file is 6.1 GB, file is 6.3 GB and 1 more.
What context length does LFM2.5 8B A1B APEX 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 LFM2.5 8B A1B APEX GGUF?
The files are on Hugging Face in the mudler/LFM2.5-8B-A1B-APEX-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 8B A1B APEX 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 8B A1B APEX on 8 GB VRAM?
Yes, the 3.64 GB quantized model requires about 5.7 GB of VRAM at 8 k context, leaving headroom for CPU and system usage.
Does this model support vision tasks?
No, LFM2.5 8B A1B APEX is a text‑only model and does not include vision capabilities.
What context length does it support?
The model supports up to 128,000 tokens, but memory estimates are given for an 8,000 token context.