LLM Name | HQQ 270M |
Repository ๐ค | https://huggingface.co/NukeverseAi/HQQ-270M |
Base Model(s) | |
Model Size | 270m |
Required VRAM | 0.5 GB |
Updated | 2025-08-22 |
Maintainer | NukeverseAi |
Model Type | gemma3_text |
Model Files | |
Supported Languages | en |
Model Architecture | Gemma3ForCausalLM |
License | other |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.55.2 |
Tokenizer Class | GemmaTokenizer |
Padding Token | <eos> |
Vocabulary Size | 262144 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Gemma 3 270M | 32K / 0.5 GB | 49079 | 567 |
Gemma 3 270M It | 32K / 0.5 GB | 67923 | 312 |
Gemma 3 270M It | 32K / 0.5 GB | 31653 | 12 |
Gemma 3 270M It MLX Bf16 | 32K / 0.9 GB | 2609 | 2 |
Gemma 3 270M It MLX 8bit | 32K / 0.5 GB | 7791 | 2 |
...mma 3 270M It Unsloth Bnb 4bit | 32K / 0.4 GB | 12183 | 1 |
Gemma 3 270M It Qat MLX 4bit | 32K / 0.2 GB | 2851 | 2 |
Gemma 3 270M It Bnb 4bit | 32K / 0.4 GB | 1353 | 3 |
...3 270M It Qat Q4 0 Unquantized | 32K / 0.5 GB | 373 | 11 |
Gemma 3 270M It 4bit | 32K / 0.2 GB | 667 | 5 |
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