LFM2.5 1.2B Thinking Proper needs about 2.3 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 13 quants, from 0.7 GB (Q4_K_M) to 2.3 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
LFM2.5 1.2B Thinking Proper – structured reasoning with XML tags
Fine‑tuned LFM2.5 1.2B model that outputs reasoning wrapped in <thinking> tags. Trained on 250 Claude 4.5 Opus high‑reasoning examples. Supports 128k context window and is licensed under Apache‑2.0.
Good at
- Structured reasoning output
- XML tag parsing
- High‑reasoning tasks
Limits
- Requires 8k+ context for best performance
- May need regen for longer reasoning
- No vision support
Best for
- Chatbots needing parseable reasoning
- AI assistants with UI toggling
- Research prototyping
Who it’s for. Developers building conversational agents that need clear reasoning traces. Researchers testing structured reasoning in LLMs. UI designers wanting to hide/show reasoning blocks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.7 GB | 2.3 GB | Fits | Get file → | |
| Q4_K_M | 0.7 GB | 2.3 GB | Fits | Get file → | |
| Q4_K_M | 0.7 GB | 2.3 GB | Fits | Get file → | |
| Q4_K_M | 0.7 GB | 2.3 GB | Fits | Get file → | |
| Q4_K_M | 0.7 GB | 2.3 GB | Fits | Get file → | |
| Q4_K_M | 0.7 GB | 2.3 GB | Fits | Get file → | |
| Q8_0 | 1.2 GB | 2.8 GB | Fits | Get file → | |
| Q8_0 | 1.2 GB | 2.8 GB | Fits | Get file → | |
| Q8_0 | 1.2 GB | 2.8 GB | Fits | Get file → | |
| Q8_0 | 1.2 GB | 2.8 GB | Fits | Get file → | |
| Q8_0 | 1.2 GB | 2.8 GB | Fits | Get file → | |
| Q8_0 | 1.2 GB | 2.8 GB | Fits | Get file → | |
| F16 | 2.3 GB | 3.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.73 GB file, ~2.3 GB VRAM at 8k context). For 12 GB VRAM, Q8_0 (1.25 GB file, ~2.8 GB VRAM). For 24 GB VRAM, F16 (2.34 GB file, ~3.9 GB VRAM). Estimates are approximate.
What GPU do you need for LFM2.5 1.2B Thinking Proper?
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 F16 (2.3 GB file, about 3.9 GB in use).
Which LFM2.5 1.2B Thinking Proper quant should you choose?
Q4_K_M is the usual starting point for LFM2.5 1.2B Thinking Proper: it balances file size and quality well. Here it is a 0.7 GB file.
The Q8_0 file is 1.2 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about LFM2.5 1.2B Thinking Proper
How much VRAM does LFM2.5 1.2B Thinking Proper need?
About 2.3 GB at Q4_K_M with an 8K context window. That is the 0.7 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 1.2B Thinking Proper on an 8 GB GPU?
Yes, with F16: the 2.3 GB file needs about 3.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM2.5 1.2B Thinking Proper GGUF?
It depends on the quant: Q4_K_M is 0.7 GB, Q4_K_M is 0.7 GB, Q4_K_M is 0.7 GB, Q4_K_M is 0.7 GB, Q4_K_M is 0.7 GB, Q4_K_M is 0.7 GB and 7 more.
What context length does LFM2.5 1.2B Thinking Proper support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download LFM2.5 1.2B Thinking Proper GGUF?
The files are on Hugging Face in the OpenTransformer/LFM2.5-1.2B-Thinking-Proper-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 1.2B Thinking Proper use?
Hugging Face lists the license as apache-2.0. 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 this model on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 2.3 GB VRAM at 8k context, fitting within 8 GB.
Does it support vision inputs?
No, the model has no vision capabilities.
What context length is required?
The model was trained with 128000 tokens; use at least 8k context for stable reasoning.