LLM EXPLORER 66,704 MODELS INDEXED

CantoneseLLM V2.0 8B Thinking by hon9kon9ize

By hon9kon9ize · 668 downloads
HF Repo ↗ Copy URL

CantoneseLLM V2.0 8B Thinking is an open-source language model by hon9kon9ize. Features: 8b LLM, VRAM: 16.4GB, Context: 40K, License: apache-2.0.

  Arxiv:2609.06970 Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3-8b   Cantonese   Conversational   En   Endpoints compatible   Grpo   Hong-kong   Qwen3   Reasoning   Region:us   Rlvr   Safetensors   Yue   Zh
Model Card on HF 🤗: https://huggingface.co/hon9kon9ize/CantoneseLLM-v2.0-8B-Thinking 

CantoneseLLM V2.0 8B Thinking Parameters and Internals

LLM NameCantoneseLLM V2.0 8B Thinking
Repository 🤗https://huggingface.co/hon9kon9ize/CantoneseLLM-v2.0-8B-Thinking 
Base Model(s)  Qwen3 8B Base   Qwen3 8B   Qwen/Qwen3-8B-Base   Qwen/Qwen3-8B
Model Size8b
Required VRAM16.4 GB
Updated2026-11-05
Maintainerhon9kon9ize
Model Typeqwen3
Model Files  16.4 GB
Supported Languageszh en
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version5.3.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Errorsreplace

Best Alternatives to CantoneseLLM V2.0 8B Thinking

Best Alternatives
Context / RAM
Downloads
Likes
PaCoRe 8B320K / 1.2 GB5448
RLVR 8B 0926320K / 1.2 GB638
...n3 8B 320K Context 10X Massive320K / 16.4 GB200
...r Of Horror Jan V1 256K Ctx 8B256K / 16.1 GB333
... BIG Jan Horror V1 256K Ctx 8B256K / 16.1 GB440
Qwen3 8B 256K Context 8X Grand256K / 16.4 GB950
...wen3 8B 192K Context 6X Larger192K / 16.4 GB550
DeepSeek R1 0528 Qwen3 8B128K / 16.4 GB17622931082
...Qwen3 8B NVFP4 W4A16 PreTensor128K / 0.9 GB4633
...1 Qwen3 8B ArliAI RpR V4 Small128K / 16.4 GB1821
Note: green Score (e.g. "73.2") means that the model is better than hon9kon9ize/CantoneseLLM-v2.0-8B-Thinking.