LLM EXPLORER 61,561 MODELS INDEXED

CustomThinker 0 8B by AGI-0

By AGI-0 · 205 downloads
HF Repo ↗ Copy URL

CustomThinker 0 8B is an open-source language model by AGI-0. Features: 8b LLM, VRAM: 16.4GB, Context: 40K, License: apache-2.0, Quantized, LLM Explorer Score: 0.2.

  Conversational   Endpoints compatible   Gguf   Q4   Quantized   Qwen3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/gr0010/CustomThinker-0-8B 

CustomThinker 0 8B Parameters and Internals

LLM NameCustomThinker 0 8B
Repository 🤗https://huggingface.co/gr0010/CustomThinker-0-8B 
Model Size8b
Required VRAM16.4 GB
Updated2026-09-19
MaintainerAGI-0
Model Typeqwen3
Model Files  5.0 GB   4.9 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   1.6 GB: 4-of-4
GGUF QuantizationYes
Quantization Typeq4|gguf|q4_k
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.55.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to CustomThinker 0 8B

Best Alternatives
Context / RAM
Downloads
Likes
DeepSeek R1 0528 Qwen3 8B GGUF128K / 2.3 GB52800436
Qwen3 8B 128K GGUF128K / 2.3 GB210628
Qwen3 8B Houdini VEX V1140K / 16.4 GB5963
AOS Qwen3 8B Grpo Merged40K / 16.4 GB4850
...S Qwen3 8B Narrated Sft Merged40K / 16.4 GB6200
AOS Qwen3 8B Narrated Merged40K / 16.4 GB4130
Qwen3 8B MedReasonPath40K / 16.4 GB3491
Qwen3 8B GGUF40K / 2.3 GB206898140
Midas FableAgent 8B40K / 16.4 GB1100
BehChat SFTv3 Ckpt1128K / 16.4 GB60
Note: green Score (e.g. "73.2") means that the model is better than gr0010/CustomThinker-0-8B.