LFM2.5 8B A1B DSpark Draft v1 needs about 0.9 GB of memory at Q8_0 (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.3 GB.
LFM2.5 8B A1B DSpark Draft v1 – a speculative drafter for llama.cpp
LFM2.5 8B A1B DSpark Draft v1 is a GGUF build of LiquidAI’s LFM2.5 model, providing a draft sidecar with 5 attention layers and a rank‑256 Markov head. It shares token embeddings and the LM head with the target model and requires pairing with a LFM2.5‑8B‑A1B‑GGUF file. The draft improves speculative decoding speed marginally.
Good at
- Reasoning
- Tools integration
- Speculative decoding
Limits
- Requires paired target model
- No vision support
- License: other
Best for
- Edge deployment with limited VRAM
- Fast draft generation in llama.cpp
- Testing speculative decoding
Who it’s for. Developers building lightweight LLM applications who need a draft sidecar for speculative decoding. The model is suitable for users who can pair it with the corresponding target GGUF file and run it via llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.4 GB | 0.9 GB | Fits | Get file → |
The only available quantization is Q8_0, file size 0.36 GB. It requires approximately 0.9 GB of VRAM at 8 k context. For tighter memory budgets, consider using a lower‑quant target model, but the draft itself remains Q8_0.
What GPU do you need for LFM2.5 8B A1B DSpark Draft v1?
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 Q8_0 (0.4 GB file, about 0.9 GB in use).
Which LFM2.5 8B A1B DSpark Draft v1 quant should you choose?
Q8_0 (0.4 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LFM2.5 8B A1B DSpark Draft v1
How much VRAM does LFM2.5 8B A1B DSpark Draft v1 need?
About 0.9 GB at Q8_0 with an 8K context window. That is the 0.4 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 DSpark Draft v1 on an 8 GB GPU?
Yes, with Q8_0: the 0.4 GB file needs about 0.9 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 DSpark Draft v1 GGUF?
It depends on the quant: Q8_0 is 0.4 GB.
What context length does LFM2.5 8B A1B DSpark Draft v1 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 DSpark Draft v1 GGUF?
The files are on Hugging Face in the magnitudedev/LFM2.5-8B-A1B-DSpark-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 DSpark Draft v1 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 draft requires about 0.9 GB of VRAM at 8 k context, leaving room for the target model within an 8 GB budget.
Does this model support vision tasks?
No, the model does not include vision capabilities.
Do I need a special license to use this model?
The model is released under an 'other' license; check the repository for specific terms.