LFM2.5 2.6B 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 7 quants, from 1.5 GB (Q3_K_L) to 5.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.
LFM2.5 2.6B – a hybrid text‑only model for on‑device agentic workloads
LFM2.5 2.6B is a 2.69B‑parameter hybrid model with a 128K context window. It is optimized for local inference and supports reasoning and tool use. The model runs in under 2.5 GB of memory on modern CPUs.
Good at
- Agentic tool use
- Long‑context reasoning
- Data extraction
Limits
- No vision support
- Not suited for coding or knowledge‑heavy tasks
- Requires 128K context for full capability
Best for
- Agentic research assistants
- RAG pipelines
- Long‑form content generation
Who it’s for. Developers building lightweight agentic applications that need a large context window. The model is ideal for users who want efficient local inference without heavy GPU requirements.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_L | 1.5 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_M | 1.7 GB | 4.2 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 → | |
| Q8_0 | 2.9 GB | 5.4 GB | Fits | Get file → | |
| BF16 | 5.4 GB | 7.9 GB | Tight | Get file → | |
| F16 | 5.4 GB | 7.9 GB | Tight | Get file → |
For 8 GB VRAM, Q4_K_M (1.67 GB) or Q5_K_M (1.94 GB) are suitable, using about 4.2 GB or 4.5 GB of RAM at 8 k context. If memory is limited to 4 GB, Q3_K_L (1.45 GB) is the smallest option, estimating 4 GB of RAM usage. Higher‑precision BF16 or F16 (5.4 GB) require more than 7.9 GB of RAM.
What GPU do you need for LFM2.5 2.6B?
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 Q3_K_L (1.5 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (2.9 GB file, about 5.4 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (5.4 GB file, about 7.9 GB in use).
Which LFM2.5 2.6B quant should you choose?
Q4_K_M is the usual starting point for LFM2.5 2.6B: it balances file size and quality well. Here it is a 1.7 GB file.
The Q8_0 file is 2.9 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q3_K_L at 1.5 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LFM2.5 2.6B
How much VRAM does LFM2.5 2.6B 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 on an 8 GB GPU?
Yes, with BF16: the 5.4 GB file needs about 7.9 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 GGUF?
It depends on the quant: Q3_K_L is 1.5 GB, Q4_K_M is 1.7 GB, Q5_K_M is 1.9 GB, Q6_K is 2.2 GB, Q8_0 is 2.9 GB, BF16 is 5.4 GB and 1 more.
What context length does LFM2.5 2.6B support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.
Where can I download LFM2.5 2.6B GGUF?
The files are on Hugging Face in the nicolasembleton/LFM2.5-2.6B-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 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 2.6B on 8 GB VRAM?
Yes, using Q4_K_M or Q5_K_M quantizations will fit within 8 GB VRAM, with estimated RAM usage of 4.2 GB or 4.5 GB at 8 k context.
Does the model support image inputs?
No, LFM2.5 2.6B is a text‑only model and does not handle vision inputs.
What context length does it need?
The model is designed for a 128K context window; using less may limit performance.