gemma4:12b-mxfp8

23M 29 minutes ago

Gemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.

vision tools thinking audio cloud e2b e4b 12b 26b 31b
... /
json
ee8112d6890f · 4.6kB
{
"architectures": [
"Gemma4UnifiedForConditionalGeneration"
],
"audio_config": {
"_name_or_path": "",
"architectures": null,
"audio_embed_dim": 640,
"chunk_size_feed_forward": 0,
"dtype": "bfloat16",
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"model_type": "gemma4_unified_audio",
"output_attentions": false,
"output_hidden_states": false,
"problem_type": null,
"return_dict": true,
"rms_norm_eps": 1e-06
},
"audio_token_id": 258881,
"boa_token_id": 256000,
"boi_token_id": 255999,
"dtype": "bfloat16",
"eoa_token_index": 258883,
"eoi_token_id": 258882,
"eos_token_id": [
1,
106
],
"image_token_id": 258880,
"initializer_range": 0.02,
"model_type": "gemma4_unified",
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"attention_k_eq_v": true,
"bos_token_id": 2,
"dtype": "bfloat16",
"enable_moe_block": false,
"eos_token_id": 1,
"final_logit_softcapping": 30.0,
"global_head_dim": 512,
"head_dim": 256,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 3840,
"hidden_size_per_layer_input": 0,
"initializer_range": 0.02,
"intermediate_size": 15360,
"layer_types": [
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention"
],
"max_position_embeddings": 262144,
"model_type": "gemma4_unified_text",
"moe_intermediate_size": null,
"num_attention_heads": 16,
"num_experts": null,
"num_global_key_value_heads": 1,
"num_hidden_layers": 48,
"num_key_value_heads": 8,
"num_kv_shared_layers": 0,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"full_attention": {
"partial_rotary_factor": 0.25,
"rope_theta": 1000000.0,
"rope_type": "proportional"
},
"sliding_attention": {
"rope_theta": 10000.0,
"rope_type": "default"
}
},
"sliding_window": 1024,
"tie_word_embeddings": true,
"top_k_experts": null,
"use_bidirectional_attention": "vision",
"use_cache": true,
"use_double_wide_mlp": false,
"vocab_size": 262144,
"vocab_size_per_layer_input": 262144
},
"tie_word_embeddings": true,
"transformers_version": "5.12.1",
"video_token_id": 258884,
"vision_config": {
"_name_or_path": "",
"architectures": null,
"chunk_size_feed_forward": 0,
"dtype": "bfloat16",
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"mm_embed_dim": 3840,
"mm_posemb_size": 1120,
"model_type": "gemma4_unified_vision",
"num_soft_tokens": 280,
"output_attentions": false,
"output_hidden_states": false,
"output_proj_dims": 3840,
"patch_size": 16,
"pooling_kernel_size": 3,
"problem_type": null,
"return_dict": true,
"rms_norm_eps": 1e-06
},
"quantization_config": {
"quant_method": "mxfp8",
"mode": "mxfp8",
"bits": 8,
"_comment": "Declares the MLX-layout tensors only. NVFP4 tensors use the compressed-tensors layout, which forces its own type and group size; group_size is deliberately omitted here so that default applies."
}
}