google/gemma-4-31B-it-qat-q4_0-unquantized-assistant
Full fine-tune vs google/gemma-4-31B-it-assistant. Fine-tune: 100% of the weights changed, across 4 of 4 layers.
Tensors changed: Embeddings 1/1, Norms 21/21, other 5/6, MLP 12/12, Attention 8/8
11 derivatives checked
- RachidAR/gemma-4-31B-it-qat-Q4_0-Q4emb-MTP-assistant-gguf: Same weights, converted
- mradermacher/gemma-4-31B-it-qat-q4_0-unquantized-assistant-GGUF: Quantization
- Gaboo/gemma-4-31B-it-qat-q4_0-assistant: Partial fine-tune
- jatucop/gemma-4-31b-drafter-4bit: Quantization
- Stabhappy/gemma-4-31B-it-qat-q4_0-unquantized-assistant-GGUF: Quantization
- mlx-community/gemma-4-31B-it-qat-assistant-4bit: Quantization
- Janvitos/gemma-4-31B-it-qat-assistant-MTP-Q8_0-GGUF: Quantization
- mlx-community/gemma-4-31B-it-qat-assistant-bf16: Same weights, repacked
- Simplepotat/gemma-4-31b-it-qat-q4_0-assistant-gguf: Quantization
- ensky0/gemma-4-31B-it-qat-q4_0-gguf-assistant: Quantization
- mlx-community/gemma-4-31B-it-qat-assistant-8bit: Quantization
1 other repos hold byte-for-byte identical weight files.