LF

LFM2.5 2.6B DSpark Draft v1

LfmGGUF by magnitudedevUpdated 2026-10-06
Download on Hugging Face
Parameters328M
Context125K
Layers5
Architecturedflash
Smallest quant0.4 GB
Quick answer

LFM2.5 2.6B 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 2.6B DSpark Draft v1 – a speculative drafter for LFM2.5-2.6B

LFM2.5 2.6B DSpark Draft v1 is a GGUF build of the LFM2.5-2.6B model, providing a speculative drafter with 5 attention layers and a rank‑256 Markov head. It shares token embeddings and the LM head with the target model and requires a paired LFM2.5‑2.6B‑GGUF file. The draft is designed for use with llama.cpp and supports exact speculative decoding.

Good at

  • Speculative decoding
  • Bidirectional draft attention
  • Exact draft verification

Limits

  • Requires paired target model
  • No vision support
  • Limited to 128000 context tokens

Best for

  • Speed‑critical inference
  • Edge deployment with limited VRAM
  • LLM drafting workflows

Who it’s for. Developers building inference pipelines with llama.cpp who need a lightweight speculative drafter. It is suitable for users who already have the LFM2.5‑2.6B‑GGUF target model and want to add draft functionality.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.4 GB 0.9 GB
Fits Get file →

The only available quantization is Q8_0, with a file size of 0.36 GB and an estimated memory usage of 0.9 GB at 8 k context. For a 4 GB VRAM budget, Q8_0 is the recommended choice. If memory is tighter, consider using a lower‑precision quant of the target model instead.

What GPU do you need for LFM2.5 2.6B 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 2.6B 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

Architecturedflash
Parameters328M
Layers5
Trained context128,000 tokens
KV cache (fp16)10 KB per token

Source

Quantized bymagnitudedev
FamilyLfm
Licenseother
Downloads (HF)1,295
Last updated2026-10-06

Frequently asked questions about LFM2.5 2.6B DSpark Draft v1

How much VRAM does LFM2.5 2.6B 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 2.6B 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 2.6B DSpark Draft v1 GGUF?

It depends on the quant: Q8_0 is 0.4 GB.

What context length does LFM2.5 2.6B 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 2.6B DSpark Draft v1 GGUF?

The files are on Hugging Face in the magnitudedev/LFM2.5-2.6B-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 2.6B 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 LFM2.5 2.6B DSpark Draft v1 on 8 GB VRAM?

Yes, the Q8_0 draft file uses 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 draft does not include vision capabilities.

What is the maximum context length for this draft?

The draft is trained with 128000 context tokens, but the effective context is limited by the target model’s context size.

Similar models

Browse all →

More from magnitudedev

All by magnitudedev →

More Lfm models

All Lfm →

Other tiny models

All tiny models →