… "mlx-community/gemma-4-26b-a4b-bf16" instead of "mlx-community/gemma-4-26B-A4B-it" The following command worked for me: ▶ mlx vlm.generate \ --model "mlx-community/gemma-4-26b-a4b-it-4bit" \ --prompt "What is the capital of France?" \ --kv-bits 3.5 \ --kv-quant-scheme turboquant Hi All Struggling t… …
… Basically my question is what is the best way to use Gemma on Qualcomm devices for Multimodal support? …
…File "/usr/local/lib/python3.11/dist-packages/transformers/models/gemma3/modeling_gemma3.py", line 880, in forward [rank0]: logits = self.lm_head(hidden_states[:, slice_indices, :]) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/usr/local…
… The sagemaker deployment https://huggingface.co/google/embeddinggemma-300m?sagemaker deploy=true is not working because it uses hugging-face tei version 1.8.0 while it should be =1.8.1 as the article mentions : "Could not start Candle backend: Could not start backend: Model is not supported\n\nCaus… …
… Across models the effect tracks the reasoning channel high in Qwen3-32B and GPT-OSS-20B, low in inline-CoT Gemma-4-31B-it . …
… Replicates on PlanBench Blocksworld and on four open-weights models Qwen3.6-35B-A3B, Gemma-4-26B-A4B-it, gpt-oss-20b, Nemotron-3-Nano-30B-A3B . …