chore(sync): update Hugging Face model catalog

[opencode-agent]

Updates model TOMLs for the huggingface sync target.

Provider	Status	Created	Updated	Deleted
Hugging Face	changed	1	0	0

Hugging Face changed files

• created: /home/runner/work/models.dev/models.dev/providers/huggingface/models/tencent/Hy4-preview.toml

Notices

Hugging Face

• 67 Hugging Face Inference Providers models were not created because their IDs could not be mapped to provider-agnostic metadata, had no live provider, or had no priced provider.
• Skipped remote IDs: prism-ml/Ternary-Bonsai-27B-gguf, meta-models/Muse-Glimmer-30B, Qwen/Qwen3-8B, inclusionAI/Ling-3.0-flash-Fin, inclusionAI/Ling-3.0-flash-VL, nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16, inclusionAI/Ling-3.0-flash, Qwen/Qwen3-4B-Instruct-2507, prism-ml/Ternary-Bonsai-27B-AWQ-4bit, swiss-ai/Apertus-v1.5-8B, swiss-ai/Apertus-v1.5-70B, Qwen/Qwen3-14B, ibm-granite/granite-4.2-8b, speakleash/Bielik-11B-v3.0-Instruct, deepseek-ai/DeepSeek-R1-Distill-Qwen-14B, zai-org/GLM-5.3-BF16, microsoft/phi-4, openai/gpt-oss-safeguard-20b, ibm-granite/granite-4.2-3b, meta-llama/Llama-4-Scout-17B-16E-Instruct, Sao10K/L3-8B-Stheno-v3.2, deepseek-ai/DeepSeek-R1-Distill-Llama-70B, nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4, meta-llama/Llama-Guard-4-12B, Qwen/Qwen2.5-Coder-7B-Instruct, meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8, CohereLabs/tiny-aya-water, deepseek-ai/DeepSeek-R1-Distill-Qwen-7B, zai-org/GLM-5.3-Flash-BF16, ibm-granite/granite-4.2-30b, CohereLabs/c4ai-command-r-08-2024, zai-org/GLM-5.2-FP8, alpindale/WizardLM-2-8x22B, CohereLabs/command-a-reasoning-08-2025, Sao10K/L3-8B-Lunaris-v1, CohereLabs/tiny-aya-earth, Qwen/Qwen3-VL-30B-A3B-Instruct, zai-org/AutoGLM-Phone-9B-Multilingual, Qwen/Qwen2.5-Coder-3B-Instruct, Qwen/Qwen3-4B-Thinking-2507, Qwen/Qwen2.5-72B-Instruct, nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16, CohereLabs/aya-vision-32b, zai-org/GLM-4.5V-FP8, NousResearch/Hermes-3-Llama-3.1-70B, CohereLabs/command-a-vision-07-2025, zai-org/GLM-4.7-FP8, deepseek-ai/DeepSeek-R1-Distill-Llama-8B, zai-org/GLM-5.1-FP8, zai-org/GLM-4.6V, baidu/ERNIE-4.5-VL-424B-A47B-Base-PT, zai-org/GLM-4.6V-FP8, deepseek-ai/DeepSeek-V3.1-Terminus, zai-org/GLM-4-32B-0414, MiniMaxAI/MiniMax-M1-80k, aisingapore/Gemma-SEA-LION-v4-27B-IT, CohereLabs/aya-expanse-32b, deepseek-ai/DeepSeek-V3.2-Exp, swiss-ai/Apertus-8B-Instruct-2509, CohereLabs/c4ai-command-r7b-12-2024, aisingapore/Qwen-SEA-LION-v4-32B-IT, CohereLabs/c4ai-command-r7b-arabic-02-2025, Qwen/Qwen2.5-VL-72B-Instruct, CohereLabs/c4ai-command-a-03-2025, CohereLabs/command-a-translate-08-2025, CohereLabs/tiny-aya-global, CohereLabs/tiny-aya-fire
• 6 local Hugging Face models were absent from the Inference Providers catalog and were retained for manual lifecycle review.
• Retained local paths: XiaomiMiMo/MiMo-V2-Flash.toml, moonshotai/Kimi-K2-Thinking.toml, Qwen/Qwen3-Embedding-8B.toml, Qwen/Qwen3-Next-80B-A3B-Thinking.toml, Qwen/Qwen3-Embedding-4B.toml, deepseek-ai/DeepSeek-V3-0324.toml

This PR was created automatically by the model sync workflow.