Get the latest setups
Models/LFM2.5 2.6B DSpark
Text / LiquidAI

LFM2.5 2.6B DSpark

LFM2.5 2.6B DSpark is a speculative-decoding draft model from Liquid AI that adapts DSpark to the LFM2.5 architecture. It serves as a drafter for the LiquidAI/LFM2.5-2.6B target model, intended to allow that model to run faster without degrading quality. It is distributed under the lfm1.0 license and has a text-generation pipeline. The model card describes use with SGLang and on-device Apple silicon via a Metal backend.

EstimatedRepository opened Aug 10, 2026Source checked 9/24/2026Version: 458cedab
LOCALRENTED GPUOPEN WEIGHTS
Freshness 71 out of 100. Repository age: 90 days old, Aug 10, 2026. Measures age, not quality.
Popularity 52 out of 100. 8,944 downloads in 30 days; 38 lifetime likes. Checked Nov 7, 2026. Measures adoption, not quality.
What do these scores mean?

Two ways to compare models. Neither score measures answer quality, benchmark performance, or whether a model fits your machine.

Freshness · release age

A new release starts at 100. The score halves every 180 days: 100 × 2^(−age in days / 180). When the release date is unavailable, a repository date is a fallback—not proof of when the model was released. Missing dates stay unscored.

Check the date source
Popularity · adoption

Downloads over the past 30 days carry 80% of the score; lifetime likes carry 20%. Both use a logarithmic scale, capped at 10 million downloads and 100,000 likes. If likes are unavailable, downloads carry all the weight. Missing download statistics stay unscored.

round(80 × min(1, log10(1 + downloads) / 7) + 20 × min(1, log10(1 + likes) / 5))

Check the statistics source
Scores as of Nov 8, 2026. Statistics checked Nov 7, 2026. Statistics are marked for refresh after 72 hours.Full scoring method

At a glance

Parameters
0.33B
Architecture
qwen3
Context length
128,000
License
lfm1.0
Disk space
0.6 GB
Software
SGLang
View the model source
MY HARDWARE

Will it run on your machine?

Save your machine to see a personalized rating and its reasoning.

Add my hardware

Best for

  • Speculative decoding as a draft model for LiquidAI/LFM2.5-2.6B
  • Faster decoding of the target model in SGLang
  • On-device decoding on Apple silicon through the Metal backend
  • Text generation when paired with the LFM2.5-2.6B target model
  • Use within the LFM2.5-DSpark family of speculative-decoding draft models

Tradeoffs

  • It is a draft model for LiquidAI/LFM2.5-2.6B and is not described as a standalone model.
  • Its license is lfm1.0, identified in the card as license: other.
  • The supplied material does not specify supported frameworks beyond SGLang or a Metal backend.
  • No independent testing or purchase recommendation is provided or implied.
  • Numerical hardware requirements, compatibility, or performance beyond the supplied figures should not be inferred.

Ways to run it

SGLang · Linux

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

python -m sglang.launch_server --model-path LiquidAI/LFM2.5-2.6B --speculative-algorithm DSPARK --speculative-draft-model-path LiquidAI/LFM2.5-2.6B-DSpark --speculative-draft-attention-backend flashinfer --disable-radix-cache --mem-fraction-static 0.75 --port 30000
Official instructions

Explore its uses

SAFETENSORSTEXT-GENERATION

Keep exploring

Text
Prism ML

Bonsai 2 · 27B

A compressed 27B-class reasoning model with publisher-provided GGUF packs and a dedicated llama.cpp fork for CUDA, Metal, and CPU.

Freshness 82 out of 100. Release age: 52 days old, Sep 17, 2026. Measures age, not quality.
Popularity 85 out of 100. 1,710,588 downloads in 30 days; 2,952 lifetime likes. Checked Nov 7, 2026. Measures adoption, not quality.
MODEL SIZE27.36B
LOCALRENTED GPU
Released Sep 17, 2026
Text
DeepSeek

DeepSeek V4.1 Flash

An open-weight model for reasoning, coding, agents, and image understanding. DeepSeek V4.1 Flash combines a 552B backbone with sparse activation and up to one million tokens of context. Choose the original checkpoint or a community uncensored variant below.

Freshness 80 out of 100. Repository age: 59 days old, Sep 10, 2026. Measures age, not quality.
Popularity 87 out of 100. 1,911,780 downloads in 30 days; 4,887 lifetime likes. Checked Nov 7, 2026. Measures adoption, not quality.
MODEL SIZE552B backbone · 8B active prefill / 16B active decode
LOCALRENTED GPU
Repository opened Sep 10, 2026
Text
Qwen

Qwen3.8

Explore 4 versions of Qwen3.8. Compare model sizes, packages, hardware requirements, and available setups.

4 versionsCompare sizes & formats
LOCALRENTED GPU
Compare versions →