RexReranker 0.6B is an open-source language model by thebajajra. Features: 0.6b LLM, VRAM: 1.2GB, Context: 40K, License: apache-2.0, LLM Explorer Score: 0.28.
Alibaba Amazon Asos Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-reranker... Bestbuy Carrefour Costco Dataset:thebajajra/amazebay-re... Decoder E-commerce Ebay Ecommerce En Endpoints compatible Etsy Flipkart Foundation-model Google Language-modeling Marketplace Model-index Overstock Qwen3 Rakuten Region:us Retail Safetensors Shein Shopify Shopping Taobao Target Text-ranking Walmart Wayfair
Model Card on HF 🤗: https://huggingface.co/thebajajra/RexReranker-0.6B
RexReranker 0.6B Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
RexReranker 0.6B Parameters and Internals
| LLM Name | RexReranker 0.6B |
| Repository 🤗 | https://huggingface.co/thebajajra/RexReranker-0.6B |
| Base Model(s) | |
| Model Size | 0.6b |
| Required VRAM | 1.2 GB |
| Updated | 2026-05-06 |
| Maintainer | thebajajra |
| Model Type | qwen3 |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen3ForCausalLM |
| License | apache-2.0 |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Transformers Version | 4.57.3 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151669 |
| Errors | replace |
Best Alternatives to RexReranker 0.6B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3 Reranker 0.6B | 40K / 1.2 GB | 1424638 | 335 |
| Qwen3 0.6B FP8 | 40K / 1.1 GB | 1715405 | 58 |
| Palindrome Sft Qwen3 | 40K / 2.4 GB | 71 | 0 |
| Meet7.5 0.6b Writer Exp | 40K / 1.2 GB | 410 | 0 |
| Meet7.5 0.6B | 40K / 1.2 GB | 347 | 0 |
| Qwen3 0.6B | 40K / 1.2 GB | 259542 | 20 |
| Medical QA | 40K / 1.2 GB | 452 | 1 |
| Meet7.1 0.6B | 40K / 1.2 GB | 164 | 0 |
| Qwen3 0.6B Instruct | 40K / 1.5 GB | 53 | 0 |
| ...ied Qwen3 0.6B Gabliterated V1 | 40K / 1.2 GB | 17 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than thebajajra/RexReranker-0.6B .
Rank the RexReranker 0.6B Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 53518 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a