Qwen3 30B A3b To 4B Onpolicy 5K Src20k 25K Freeze Rock by RockToken

 »  All LLMs  »  RockToken  »  Qwen3 30B A3b To 4B Onpolicy 5K Src20k 25K Freeze Rock   URL Share it on

Qwen3 30B A3b To 4B Onpolicy 5K Src20k 25K Freeze Rock is an open-source language model by RockToken. Features: 30b LLM, VRAM: 8.9GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.27.

Base model:finetune:rocktoken/... Base model:rocktoken/qwen3 30b...   Conversational   En   Endpoints compatible   Knowledge-distillation   Math   On-policy   Qwen3   Region:us   Safetensors   Sharded   Tensorflow   Token-freeze-kd

Qwen3 30b A3b To 4b Onpolicy 5k Src20k 25k Freeze Rock Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Qwen3 30B A3b To 4B Onpolicy 5K Src20k 25K Freeze Rock Parameters and Internals

LLM NameQwen3 30b A3b To 4b Onpolicy 5k Src20k 25k Freeze Rock
Repository 🤗https://huggingface.co/RockToken/qwen3_30b_a3b_to_4b_onpolicy_5k_src20k-25k_freeze_rock 
Base Model(s)  ...n3 30b A3b To 4b Offpolicy 20k   RockToken/qwen3_30b_a3b_to_4b_offpolicy_20k
Model Size30b
Required VRAM8.9 GB
Updated2026-05-04
MaintainerRockToken
Model Typeqwen3
Model Files  5.0 GB: 1-of-2   3.9 GB: 2-of-2
Supported Languagesen
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.57.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Errorsreplace

Best Alternatives to Qwen3 30B A3b To 4B Onpolicy 5K Src20k 25K Freeze Rock

Best Alternatives
Context / RAM
Downloads
Likes
...n3 30b A3b To 4b Offpolicy 20k256K / 17.6 GB1360
Qwen3 30B A3B FP440K / 20.7 GB12011
Note: green Score (e.g. "73.2") means that the model is better than RockToken/qwen3_30b_a3b_to_4b_onpolicy_5k_src20k-25k_freeze_rock.

Rank the Qwen3 30B A3b To 4B Onpolicy 5K Src20k 25K Freeze Rock 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! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 53472 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a