Model reference · open weights

Fast-dDrive

Fast-dDrive is an open-weight language model from Efficient-Large-Model, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

LLMs Efficient-Large-Model 1 variants 68 downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What Fast-dDrive is

Fast-dDrive Fast-dDrive is a block-diffusion Vision-Language-Action (VLA) model for end-to-end autonomous driving, built on Qwen2.5-VL-3B. It pairs section-aware structured-diffusion training (SASD) with scaffold-aware speculative decoding (Scaffold Spec) and an optional shared-prefix multi-trajectory inference scaling scheme, and reaches SOTA accuracy on the Waymo Open Dataset End-to-End Driving (WOD-E2E) benchmark at over 200 tokens / second on a single H100. Quick start Inference paths This release exposes three decoding paths as bound methods on the model: Important: scaffoldspeculativesample and its multi-traj variant must be run with confidencethreshold=0.0 to reproduce the paper numbers. Running at 0.9 silently degrades both ADE and throughput. Headline results — WOD-E2E test set (single H100) On the WOD-E2E val set, Scaffold Spec runs at 1919 ms / sample (4.1× over the AR baseline); fused with SGLang the same configuration drops to 665 ms / sample at 608.5 TPS — the 11.8× / 12× speedup over AR cited in the paper. Files - modeling.py — model definition (FastdDriveForConditionalGeneration) - configuration.py — config classes - sectionutils.py — scaffold construction + section-aligned block index utilities - generationutils.py — the three inference paths, attached to the model class on import - config.json, generationconfig.json, preprocessorconfig.json, chattemplate.jinja, tokenizer files — standard HF artifacts - model-0000{1..4}-of-00004.safetensors — model weights (4 shards) Citation

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

MakerEfficient-Large-Model
TypeLanguage models
Parameters (lead)235M
Variants1
Runs withtransformers
Released2026-05-30
Popularity68 downloads / month
Likes3
LicenceOpen weights

How it works

How language models work

Your prompttext / messagesTransformerattention over tokensNext-token loopgenerate + streamResponsetext · tool callsA language model reads your tokens and predicts the next one, again and again, streaming the reply back.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
Fast-dDrive235MBF16~0.5 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys fast-ddrive for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (fast-ddrive below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"fast-ddrive","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Tags

transformers safetensors fast_d_drive feature-extraction block-diffusion vision-language-action autonomous-driving qwen2.5-vl image-text-to-text conversational custom_code

Papers

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want Fast-dDrive on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More language models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms