Model Type |
| |||
Additional Notes |
| |||
Input Output |
|
LLM Name | Gemma 2B Bnb 4bit |
Repository ๐ค | https://huggingface.co/unsloth/gemma-2b-bnb-4bit |
Model Size | 2b |
Required VRAM | 2.1 GB |
Updated | 2025-07-08 |
Maintainer | unsloth |
Model Type | gemma |
Model Files | |
Supported Languages | en |
Quantization Type | 4bit |
Model Architecture | GemmaForCausalLM |
License | apache-2.0 |
Context Length | 8192 |
Model Max Length | 8192 |
Transformers Version | 4.44.2 |
Tokenizer Class | GemmaTokenizer |
Padding Token | <pad> |
Vocabulary Size | 256000 |
Torch Data Type | bfloat16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
... 2B It Hermes Function Calling | 0 | 13 | 5 GB |
Gemma Help Tiny Sft | 1 | 62 | 5 GB |
Emo AI 3B | 1 | 30 | 5 GB |
Jenna Gemma V01 Gguf 8bit | 1 | 16 | 2 GB |
Jenna Gemma V01 Gguf Q4 | 0 | 14 | 1 GB |
Jenna Gemma V01 Gguf 16bit | 0 | 12 | 5 GB |
Test Model | 0 | 29 | 2 GB |
PRIME DeCyphers Final | 1 | 58 | 5 GB |
Gemma 2B Malayalam Merged | 1 | 47 | 5 GB |
Mode Gemma | 0 | 24 | 2 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Vi Gemma 2B RAG | 8K / 5.1 GB | 1819 | 13 |
... 2B It Hermes Function Calling | 8K / 5.1 GB | 13 | 0 |
Gemma 1.1 2B It Bnb 4bit | 8K / 2.1 GB | 2952 | 5 |
Codegemma 2B Bnb 4bit | 8K / 2.1 GB | 1914 | 1 |
Gemma 2B It Bnb 4bit | 8K / 2.1 GB | 3989 | 20 |
Gemma 1.1 2B It 4bit | 8K / 2.2 GB | 1888 | 3 |
My AwesomeFinance Model | 8K / 2.1 GB | 33 | 0 |
... 2.8 Gemma 2B HQQ 2bit Smashed | 8K / 1.6 GB | 28 | 0 |
Emo AI 3B | 8K / 5.1 GB | 30 | 1 |
... 2.8 Gemma 2B HQQ 4bit Smashed | 8K / 2.1 GB | 21 | 0 |
๐ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐