Model reference · open weights

LaSER-Qwen3

LaSER-Qwen3 is an open-weight embedding model from Alibaba-NLP, 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.

Embeddings Alibaba-NLP 3 variants 693 downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What LaSER-Qwen3 is

LaSER-Qwen3-0.6B LaSER (Latent Space Explicit Reasoning) is a self-distillation framework that internalizes explicit Chain-of-Thought reasoning into the latent space of dense retrievers, enabling the model to "think silently" through continuous latent tokens. LaSER-Qwen3-0.6B is a 0.6B-parameter dense retriever built on Qwen/Qwen3-0.6B. 📄 Paper: LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval 💻 Code: https://github.com/ignorejjj/LaSER Model Summary How It Works Unlike standard dense retrievers that encode queries in a single forward pass, LaSER generates K continuous latent thinking tokens autoregressively in the embedding space: 1. Encode the input text into embeddings 2. At each thinking step, project the last hidden state through the LM head → softmax → compute a probability-weighted soft token from the embedding table 3. Append the soft token and repeat for K steps (using KV caching for efficiency) 4. Mean-pool the hidden states from all K thinking steps → L2 normalize This enables complex reasoning while maintaining the inference efficiency of standard dense retrievers (~1.7× latency overhead, only ~0.3% of rewrite-then-retrieve pipelines). Usage Direct Usage with Transformers Batch Encoding Evaluation Results BRIGHT Benchmark (nDCG@10) — In-Domain FollowIR & BrowseComp-Plus — Out-of-Domain † indicates methods that use an external LLM to rewrite queries during inference. Training Details - Training Data: 81K query-document pairs from ReasonEmb, each with a CoT reasoning path generated by GPT-4o-mini - Method: LoRA fine-tuning (r=64, α=32) for 1 epoch on 4×A100 GPUs - Loss: Contrastive learning + Output-level KL distillation (λ₂=10) + Process-level trajectory alignment (λ₃=0.1) - Temperature: τ=0.02 - Thinking Steps: K=3 Model Family Citation

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

Specifications

What it is

MakerAlibaba-NLP
TypeEmbedding models
Parameters (lead)596M
Context40k tokens
Variants3
Runs withtransformers
Based onQwen/Qwen3-0.6B
Released2026-03-31
Popularity693 downloads / month
Likes6
LicenceOpen weights

How it works

How embedding models work

Your textsentence / documentEncodermaps meaningVectorlist of numbersAn embedding model turns text into a vector, so similar meanings sit close together — the basis of search and RAG.

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
LaSER-Qwen3-0.6B596MBF16~1.4 GBWeights ↗
LaSER-Qwen3-8B8.2BBF16~18.8 GBWeights ↗
LaSER-Qwen3-4B4.0BBF16~9.3 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys laser-qwen3 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (laser-qwen3 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"laser-qwen3","input":"text to embed"}'

Details

Languages, data & research

Languages

en

Trained / evaluated on

jinjiajie/LaSER-Training

Tags

transformers safetensors qwen3 text-generation dense-retrieval latent-reasoning embeddings information-retrieval feature-extraction en dataset:jinjiajie/LaSER-Training text-embeddings-inference endpoints_compatible

Papers

Licence

Open weights

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

Sources

Weights & code

Want LaSER-Qwen3 on EU-owned hardware?

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

Explore

More embedding models

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