Gemma 3 1B It Qat Q4 0 Unquantized is an open-source language model by google. Features: 1b LLM, VRAM: 2GB, Context: 32K, License: gemma, Quantized, LLM Explorer Score: 0.17.
| LLM Name | Gemma 3 1B It Qat Q4 0 Unquantized |
| Repository π€ | https://huggingface.co/google/gemma-3-1b-it-qat-q4_0-unquantized |
| Base Model(s) | |
| Model Size | 1b |
| Required VRAM | 2 GB |
| Updated | 2026-07-14 |
| Maintainer | |
| Model Type | gemma3_text |
| Model Files | |
| Quantization Type | q4|q4_0 |
| Model Architecture | Gemma3ForCausalLM |
| License | gemma |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.52.0.dev0 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 262144 |
| Torch Data Type | bfloat16 |
Model |
Likes |
Downloads |
VRAM |
|---|---|---|---|
| ...a 3 1B It Qat Unsloth Bnb 4bit | 2 | 132 | 1 GB |
| Gemma 3 1B It Qat Abliterated | 2 | 19 | 4 GB |
| Gemma 3 1B It Qat Bnb 4bit | 2 | 99 | 1 GB |
| Gemma 3 1B It Qat | 5 | 57 | 2 GB |
| Amoral Gemma3 1B V2 Qat | 2 | 10 | 2 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Gemma 3 1B Hindi Instruct | 32K / 2 GB | 41 | 1 |
| Gemma 3 1B It Qat 4bit | 32K / 0.7 GB | 34167 | 5 |
| Gemma 3 1B It Unsloth Bnb 4bit | 32K / 1 GB | 15646 | 10 |
| Gemma 3 1B It 4bit | 32K / 0.7 GB | 6681 | 4 |
| Gemma 3 1B It Pretrain | 32K / 2 GB | 8 | 0 |
| Gema4b | 32K / 2 GB | 15 | 0 |
| Gemma 3 1B It Bnb 4bit | 32K / 1 GB | 1474 | 10 |
| ...a 3 1B It Qat Unsloth Bnb 4bit | 32K / 1 GB | 132 | 2 |
| Gemma 3 1B It Qat Abliterated | 32K / 4 GB | 19 | 2 |
| Gemma 3 1B It Qat Bnb 4bit | 32K / 1 GB | 99 | 2 |