zaydiscold
/

Qwopus3.6-35B-A3B-v1-MLX-bf16

Mixture of Experts

Model card Files Files and versions

Qwopus3.6-35B-A3B-v1-MLX-bf16 / smoke-bf16bit.txt

zaydiscold's picture

Upload folder using huggingface_hub

a4a502f verified about 1 month ago

history blame contribute delete

2.16 kB

	Validation for bf16-bit
	Model path: /Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16
	Size GiB: 65
	Checked at UTC: 2026-05-07T11:43:49Z

	Files:
	/Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16/README.md
	/Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16/chat_template.jinja
	/Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16/config.json
	/Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16/model-00001-of-00014.safetensors
	/Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16/model-00002-of-00014.safetensors
	/Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16/model-00003-of-00014.safetensors
	/Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16/model-00004-of-00014.safetensors
	/Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16/model-00005-of-00014.safetensors
	/Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16/model-00006-of-00014.safetensors
	/Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16/model-00007-of-00014.safetensors
	/Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16/model-00008-of-00014.safetensors
	/Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16/model-00009-of-00014.safetensors
	/Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16/model-00010-of-00014.safetensors
	/Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16/model-00011-of-00014.safetensors
	/Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16/model-00012-of-00014.safetensors
	/Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16/model-00013-of-00014.safetensors
	/Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16/model-00014-of-00014.safetensors
	/Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16/model.safetensors.index.json
	/Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16/tokenizer.json
	/Users/flow/mlx-qwopus/models/Qwopus3.6-35B-A3B-v1-MLX-bf16/tokenizer_config.json

	STRUCTURAL_VALIDATION=pass
	GENERATION_SMOKE=skipped_on_flow_m1_16gb
	Reason: model artifact is too large for this 16GB Mac mini; earlier generation attempt hit Metal OOM. Run generation after pulling to a larger Apple Silicon machine.