TheDrummer/Artemis-31B-v1.1
Full fine-tune vs google/gemma-4-31B-it. Fine-tune: 100% of the weights changed, across 60 of 60 layers.
Tensors changed: Embeddings 4/4, Norms 0/523, other 0/62, MLP 261/261, Attention 338/338
8 derivatives checked
- bartowski/TheDrummer_Artemis-31B-v1.1-GGUF: Same weights, converted (fewer layers)
- mradermacher/Artemis-31B-v1.1-i1-GGUF: Quantization (fewer layers)
- mradermacher/Artemis-31B-v1.1-GGUF: Quantization (fewer layers)
- vwdubb/Artemis-31B-v1.1-FP8: Quantization
- ailexleon/Artemis-31B-v1.1-mlx-4Bit: Quantization
- ailexleon/Artemis-31B-v1.1-mlx-6Bit: Quantization
- mobbitxt/Artemis-31B-v1.1-oQ4e: Quantization
- McG-221/Artemis-31B-v1.1-mlx-8Bit: Quantization