LFM2.5 8B A1B ThinkingCap needs about 0.8 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 8 quants, from 0.2 GB (Q4_K_M) to 16.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.3 GB.
LFM2.5 8B A1B ThinkingCap – a reasoning‑focused GGUF model
LFM2.5 8B A1B ThinkingCap is a 8.47 billion‑parameter model built on the dflash architecture. It is trained with supervised fine‑tuning and direct preference optimization to produce structured reasoning within a defined contract. The model supports reasoning and tool usage.
Good at
- Reasoning with structured output
- Tool integration
- English and Spanish fluency
Limits
- No vision support
- Requires 128 000 token context
- License is other
Best for
- Chatbots needing deterministic reasoning
- Tool‑enabled assistants
- Multilingual support
Who it’s for. Developers building AI assistants that require clear internal reasoning and tool calls. The model is suitable for applications that need structured, deterministic responses in English and Spanish.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.2 GB | 0.8 GB | Fits | Get file → | |
| BF16 | 0.7 GB | 1.2 GB | Fits | Get file → | |
| — | 4.9 GB | 5.5 GB | Fits | Get file → | |
| — | 5.0 GB | 5.6 GB | Fits | Get file → | |
| Q6_K | 7.0 GB | 7.5 GB | Tight | Get file → | |
| — | 7.0 GB | 7.6 GB | Tight | Get file → | |
| Q8_0 | 9.0 GB | 9.6 GB | Too big | Get file → | |
| BF16 | 16.9 GB | 17.5 GB | Too big | Get file → |
For 8 GB VRAM use the Q4_K_M quant (0.2 GB file, ~0.8 GB memory at 8 k context). For 16 GB VRAM the BF16 quant (0.66 GB file, ~1.2 GB memory) is suitable. Larger quants such as Q6_K or Q8_0 require more than 16 GB VRAM.
What GPU do you need for LFM2.5 8B A1B ThinkingCap?
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 BF16 (0.7 GB file, about 1.2 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (5.0 GB file, about 5.6 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (7.0 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.0 GB file, about 9.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.0 GB file, about 9.6 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (16.9 GB file, about 17.5 GB in use).
Which LFM2.5 8B A1B ThinkingCap quant should you choose?
Q4_K_M is the usual starting point for LFM2.5 8B A1B ThinkingCap: it balances file size and quality well. Here it is a 0.2 GB file.
The Q8_0 file is 9.0 GB, about 45.1 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
Source
Frequently asked questions about LFM2.5 8B A1B ThinkingCap
How much VRAM does LFM2.5 8B A1B ThinkingCap need?
About 0.8 GB at Q4_K_M with an 8K context window. That is the 0.2 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 8B A1B ThinkingCap on an 8 GB GPU?
Yes, with the smaller files: the 7.0 GB file needs about 7.6 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 ThinkingCap GGUF?
It depends on the quant: Q4_K_M is 0.2 GB, BF16 is 0.7 GB, file is 4.9 GB, file is 5.0 GB, Q6_K is 7.0 GB, file is 7.0 GB and 2 more.
What context length does LFM2.5 8B A1B ThinkingCap support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.3 GB at 32K.
Where can I download LFM2.5 8B A1B ThinkingCap GGUF?
The files are on Hugging Face in the Davd-b01/LFM2.5-8B-A1B-ThinkingCap-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 ThinkingCap 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 this model on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 0.8 GB of VRAM at 8 k context, fitting within an 8 GB budget.
Does the model support vision tasks?
No, the model does not include vision capabilities.
What context length is supported?
The model was trained with a context of 128 000 tokens.