LLM EXPLORER 57,252 MODELS INDEXED

Gemma 3 1B It Qat Int4 Unquantized by google

By google · 113 downloads

Gemma 3 1B It Qat Int4 Unquantized is an open-source language model by google. Features: 1b LLM, VRAM: 2GB, Context: 32K, License: gemma, LLM Explorer Score: 0.18.

  Arxiv:1705.03551   Arxiv:1810.12440   Arxiv:1903.00161   Arxiv:1904.09728   Arxiv:1905.07830   Arxiv:1905.10044   Arxiv:1907.10641   Arxiv:1908.02660   Arxiv:1910.11856   Arxiv:1911.01547   Arxiv:1911.11641   Arxiv:2009.03300   Arxiv:2103.03874   Arxiv:2104.12756   Arxiv:2106.03193   Arxiv:2107.03374   Arxiv:2108.07732   Arxiv:2110.14168   Arxiv:2203.10244   Arxiv:2210.03057   Arxiv:2304.06364   Arxiv:2311.12022   Arxiv:2311.16502   Arxiv:2312.11805   Arxiv:2404.12390   Arxiv:2404.16816   Arxiv:2502.12404   Arxiv:2502.21228 Base model:finetune:google/gem... Base model:google/gemma-3-1b-i...   Conversational   Endpoints compatible   Gemma   Gemma3   Gemma3 text   Google   Region:us   Safetensors

Gemma 3 1B It Qat Int4 Unquantized Parameters and Internals

LLM NameGemma 3 1B It Qat Int4 Unquantized
Repository πŸ€—https://huggingface.co/google/gemma-3-1b-it-qat-int4-unquantized 
Base Model(s)  Gemma 3 1B It   google/gemma-3-1b-it
Model Size1b
Required VRAM2 GB
Updated2026-08-05
Maintainergoogle
Model Typegemma3_text
Model Files  2.0 GB
Model ArchitectureGemma3ForCausalLM
Licensegemma
Context Length32768
Model Max Length32768
Transformers Version4.52.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size262144
Torch Data Typebfloat16

Best Alternatives to Gemma 3 1B It Qat Int4 Unquantized

Best Alternatives
Context / RAM
Downloads
Likes
Gemma3 1B Sft Reasoning 232K / 2.6 GB340
Gemma 3 1B It32K / 2 GB8632822
Gemma 3 1B Pt32K / 2 GB42156
Gemma 3 1B It32K / 2 GB39591681053
Model After Sft V232K / 2 GB4920
Ganda Gemma Fln Bridge32K / 2 GB5840
Gemma 3 1B Pt32K / 2 GB75224196
...1B It OpenCode Title Generator32K / 2 GB90
... It Wildjailbreak 9K Subsample32K / 2 GB140
...Gemma 3 1B It Datav3 Only Mask32K / 2.6 GB50
Note: green Score (e.g. "73.2") means that the model is better than google/gemma-3-1b-it-qat-int4-unquantized.