LLM EXPLORER 60,958 MODELS INDEXED

BehChat SFTv3 Ckpt3 by zypchn

By zypchn · 87 downloads
HF Repo ↗ Copy URL

BehChat SFTv3 Ckpt3 is an open-source language model by zypchn. Features: 8b LLM, VRAM: 16.4GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.24.

Base model:finetune:unsloth/de... Base model:unsloth/deepseek-r1...   Conversational   En   Endpoints compatible   Qwen3   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/zypchn/BehChat-SFTv3-ckpt3 

BehChat SFTv3 Ckpt3 Parameters and Internals

LLM NameBehChat SFTv3 Ckpt3
Repository 🤗https://huggingface.co/zypchn/BehChat-SFTv3-ckpt3 
Model Nameunsloth/DeepSeek-R1-0528-Qwen3-8B
Base Model(s)  DeepSeek R1 0528 Qwen3 8B   unsloth/DeepSeek-R1-0528-Qwen3-8B
Model Size8b
Required VRAM16.4 GB
Updated2026-05-20
Maintainerzypchn
Model Typeqwen3
Model Files  4.9 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   1.6 GB: 4-of-4
Supported Languagesen
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Tokenizer ClassLlamaTokenizerFast
Padding Token<|PAD_TOKEN|>
Vocabulary Size151936
Torch Data Typebfloat16

Best Alternatives to BehChat SFTv3 Ckpt3

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
...Reason 8B Pretrain Competition128K / 16.8 GB2440
Marco DeepResearch 8B128K / 16.3 GB46534
Note: green Score (e.g. "73.2") means that the model is better than zypchn/BehChat-SFTv3-ckpt3.