Get the latest setups
Models/LFM2.5 VL 3B DSpark/LFM2.5 VL 3B DSpark
Text / LiquidAI

LFM2.5 VL 3B DSpark

LFM2.5-VL-3B-DSpark is an experimental speculative-decoding draft model for the vision-language target model LiquidAI/LFM2.5-VL-3B. It is intended to enable faster decoding while preserving the target model's output. The source lists compatibility with LFM2.5-VL-3B and its GGUF counterpart, and describes draft model details such as 279.5M BF16 parameters, a specified backbone configuration, Markov and confidence heads, and a vocabulary of 128,000.

EstimatedRepository opened Sep 18, 2026Source checked 9/24/2026Version: af77e930
LOCALRENTED GPUOPEN WEIGHTS
Freshness 90 out of 100. Repository age: 27 days old, Sep 18, 2026. Measures age, not quality.
Popularity 40 out of 100. 1,115 downloads in 30 days; 20 lifetime likes. Checked Oct 15, 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 Oct 15, 2026. Statistics checked Oct 15, 2026. Statistics are marked for refresh after 72 hours.Full scoring method

At a glance

Parameters
0.28B
Architecture
qwen3
Context length
128,000
License
lfm1.0
Disk space
0.5 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-VL-3B
  • Faster decoding of vision-language tasks without changing target outputs under greedy decoding
  • Use with SGLang on a single H100, where the source reports faster decoding
  • Use with MLX-VLM on Apple silicon at block size 8
  • Use with llama.cpp via the LFM2.5-VL-3B-GGUF target and its corresponding GGUF drafter

Tradeoffs

  • Requires pairing with the corresponding target model, such as LFM2.5-VL-3B or its GGUF version
  • Experimental draft model intended for speculative decoding, not standalone use
  • On Apple silicon the drafter uses block size 8 rather than 9
  • Acceptance and speedup depend on hardware and runtime overhead
  • No broad general-purpose or cross-model use is established by the supplied facts

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-VL-3B --speculative-algorithm DSPARK --speculative-draft-model-path LiquidAI/LFM2.5-VL-3B-DSpark --speculative-draft-attention-backend flashinfer --speculative-dspark-block-size 9 --disable-radix-cache --mem-fraction-static 0.8 --port 30000
Official instructions

Explore its uses

SAFETENSORSIMAGE-TEXT-TO-TEXT

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 90 out of 100. Release age: 28 days old, Sep 17, 2026. Measures age, not quality.
Popularity 90 out of 100. 4,849,199 downloads in 30 days; 2,697 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.
MODEL SIZE27.36B
LOCALRENTED GPU
Released Sep 17, 2026
Text
DeepSeek

DeepSeek V4.1 Flash

A multimodal reasoning model with a compressed key-value cache, published as open weights.

Freshness 87 out of 100. Repository age: 35 days old, Sep 10, 2026. Measures age, not quality.
Popularity 84 out of 100. 1,238,583 downloads in 30 days; 4,519 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.
Arena Open Source Text: rank 5 of 225. Ranked model: deepseek-v4.1-flash-max. Export dated Oct 13, 2026. Source checked Oct 15, 2026. Human preference ranking, not hardware suitability.+3
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 →
LFM2.5 VL 3B DSpark: hardware, VRAM & setup | YouRunAI