GitHub
187.8K
Download
Models
Docs
Pricing
Sign in
Download
Models
Docs
Pricing
Sign in
tsarihan
/
qwen3.8
:27b-jc-mlx
354
Downloads
Updated
4 days ago
Qwen3.8-27B community "JC" uncensored fine-tune, one-command local: Q4_K_M GGUF + F16 mmproj vision, plus an MLX NVFP4 tag for Apple Silicon. Vision, tools, thinking, 262K context.
Qwen3.8-27B community "JC" uncensored fine-tune, one-command local: Q4_K_M GGUF + F16 mmproj vision, plus an MLX NVFP4 tag for Apple Silicon. Vision, tools, thinking, 262K context.
Cancel
vision
tools
thinking
qwen3.8:27b-jc-mlx
...
/
json
42337c418d61 ยท 2.9kB
{"architectures": ["Qwen3_5ForConditionalGeneration"], "image_token_id": 248056, "language_model_only": false, "model_type": "qwen3_5", "text_config": {"attention_bias": false, "attention_dropout": 0.0, "attn_output_gate": true, "bos_token_id": 248044, "dtype": "bfloat16", "eos_token_id": 248044, "full_attention_interval": 4, "head_dim": 256, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 17408, "layer_types": ["linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention"], "linear_conv_kernel_dim": 4, "linear_key_head_dim": 128, "linear_num_key_heads": 16, "linear_num_value_heads": 48, "linear_value_head_dim": 128, "mamba_ssm_dtype": "float32", "max_position_embeddings": 262144, "model_type": "qwen3_5_text", "mtp_num_hidden_layers": 0, "num_attention_heads": 24, "num_hidden_layers": 64, "num_key_value_heads": 4, "output_gate_type": "swish", "pad_token_id": null, "partial_rotary_factor": 0.25, "rms_norm_eps": 1e-06, "rope_parameters": {"mrope_interleaved": true, "mrope_section": [11, 11, 10], "partial_rotary_factor": 0.25, "rope_theta": 10000000, "rope_type": "default"}, "tie_word_embeddings": false, "use_cache": true, "vocab_size": 248320}, "tie_word_embeddings": false, "transformers_version": "5.8.0.dev0", "video_token_id": 248057, "vision_config": {"deepstack_visual_indexes": [], "depth": 27, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 1152, "in_channels": 3, "initializer_range": 0.02, "intermediate_size": 4304, "model_type": "qwen3_5", "num_heads": 16, "num_position_embeddings": 2304, "out_hidden_size": 5120, "patch_size": 16, "spatial_merge_size": 2, "temporal_patch_size": 2}, "vision_end_token_id": 248054, "vision_start_token_id": 248053}