LFM2.5 2.6B GGUF shards needs about 3.8 GB of memory at IQ2_XS (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 48 quants, from 0.0 GB to 5.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.
LFM2.5 2.6B GGUF shards – a hybrid model for on‑device agentic workloads
LFM2.5 2.6B is a 2.69B‑parameter, text‑only model with a 128K context window. It is optimized for agentic tasks, tool use, and long‑context workflows. The model is available in multiple GGUF quantizations for efficient inference.
Good at
- Agentic tool use
- Long‑context reasoning
- Data extraction
Limits
- Large context requires high VRAM
- No vision support
- License is other, not standard
Best for
- RAG pipelines
- Agentic research assistants
- Long‑form content generation
Who it’s for. Developers building on‑device agents or RAG systems that need a large context window and efficient inference. The model is suitable for CPU or GPU inference with a suitable quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.5 GB | Fits | Get file → | |
| Q1_0 | 0.4 GB | 2.9 GB | Fits | Get file → | |
| Q1_0 | 0.4 GB | 2.9 GB | Fits | Get file → | |
| IQ1_S | 0.5 GB | 3.0 GB | Fits | Get file → | |
| IQ1_M | 0.6 GB | 3.1 GB | Fits | Get file → | |
| IQ1_M | 0.6 GB | 3.1 GB | Fits | Get file → | |
| IQ2_XXS | 0.7 GB | 3.2 GB | Fits | Get file → | |
| TQ2_0 | 0.7 GB | 3.2 GB | Fits | Get file → | |
| Q2_0 | 0.8 GB | 3.3 GB | Fits | Get file → | |
| Q2_0 | 0.8 GB | 3.3 GB | Fits | Get file → | |
| IQ2_XS | 0.8 GB | 3.3 GB | Fits | Get file → | |
| IQ2_S | 0.9 GB | 3.4 GB | Fits | Get file → | |
| IQ2_S | 0.9 GB | 3.4 GB | Fits | Get file → | |
| Q2_K | 0.9 GB | 3.4 GB | Fits | Get file → | |
| Q2_K | 0.9 GB | 3.4 GB | Fits | Get file → | |
| IQ1_S | 1.0 GB | 3.5 GB | Fits | Get file → | |
| IQ3_XXS | 1.0 GB | 3.6 GB | Fits | Get file → | |
| IQ3_XXS | 1.0 GB | 3.6 GB | Fits | Get file → | |
| IQ2_XXS | 1.2 GB | 3.7 GB | Fits | Get file → | |
| IQ3_S | 1.2 GB | 3.7 GB | Fits | Get file → | |
| Q3_K | 1.2 GB | 3.7 GB | Fits | Get file → | |
| IQ3_S | 1.2 GB | 3.7 GB | Fits | Get file → | |
| Q3_K | 1.2 GB | 3.7 GB | Fits | Get file → | |
| IQ2_XS | 1.2 GB | 3.8 GB | Fits | Get file → | |
| IQ4_XS | 1.4 GB | 4.0 GB | Fits | Get file → | |
| MXFP4 | 1.4 GB | 4.0 GB | Fits | Get file → | |
| IQ4_XS | 1.4 GB | 4.0 GB | Fits | Get file → | |
| MXFP4 | 1.4 GB | 4.0 GB | Fits | Get file → | |
| IQ4_NL | 1.5 GB | 4.0 GB | Fits | Get file → | |
| — | 1.5 GB | 4.0 GB | Fits | Get file → | |
| Q4_0 | 1.5 GB | 4.0 GB | Fits | Get file → | |
| Q4_K | 1.5 GB | 4.0 GB | Fits | Get file → | |
| IQ4_NL | 1.5 GB | 4.0 GB | Fits | Get file → | |
| — | 1.5 GB | 4.0 GB | Fits | Get file → | |
| Q4_0 | 1.5 GB | 4.0 GB | Fits | Get file → | |
| Q4_K | 1.5 GB | 4.0 GB | Fits | Get file → | |
| Q4_1 | 1.7 GB | 4.2 GB | Fits | Get file → | |
| Q4_1 | 1.7 GB | 4.2 GB | Fits | Get file → | |
| Q5_0 | 1.9 GB | 4.4 GB | Fits | Get file → | |
| Q5_K | 1.9 GB | 4.4 GB | Fits | Get file → | |
| Q5_0 | 1.9 GB | 4.4 GB | Fits | Get file → | |
| Q5_K | 1.9 GB | 4.4 GB | Fits | Get file → | |
| Q5_1 | 2.0 GB | 4.5 GB | Fits | Get file → | |
| Q5_1 | 2.0 GB | 4.5 GB | Fits | Get file → | |
| Q6_K | 2.2 GB | 4.7 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 → |
For 8 GB VRAM, use Q4_K or Q4_0 (≈4 GB memory). For 4 GB VRAM, choose Q3_K or IQ3_S (≈3.6–3.7 GB). For 2 GB VRAM, use Q2_K or IQ2_XS (≈3.3 GB). File sizes are small, but memory estimates are approximate.
What GPU do you need for LFM2.5 2.6B GGUF shards?
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 IQ4_NL (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 GGUF shards quant should you choose?
IQ2_XS (1.2 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
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 LFM2.5 2.6B GGUF shards
How much VRAM does LFM2.5 2.6B GGUF shards need?
About 3.8 GB at IQ2_XS with an 8K context window. That is the 1.2 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 GGUF shards 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 shards GGUF?
It depends on the quant: file is 0.0 GB, Q1_0 is 0.4 GB, Q1_0 is 0.4 GB, IQ1_S is 0.5 GB, IQ1_M is 0.6 GB, IQ1_M is 0.6 GB and 42 more.
What context length does LFM2.5 2.6B GGUF shards support?
The GGUF header lists a trained context length of 131,072 tokens (128K). 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 shards GGUF?
The files are on Hugging Face in the Arki05/LFM2.5-2.6B-GGUF-shards 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 GGUF shards 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 or Q4_0 quantizations will fit within 8 GB VRAM with about 4 GB memory usage.
Does this model support image inputs?
No, LFM2.5 2.6B is a text‑only model and does not support vision.
What license applies to this model?
The model is released under the LFM Open License v1.0, which is not a standard open source license.