Repository: localaiLicense: apache-2.0
LLM-jp-4-33B-thinking is an Apache-2.0 Japanese and English reasoning model from Japan's National Institute of Informatics. Its dense Llama architecture has 33 billion parameters and a 65K-token context window. The model was aligned with supervised fine-tuning and DPO for multi-turn conversation and instruction following. This default entry uses the 20.2 GB Q4_K_M GGUF. The official 66.4 GB BF16 weights are available as a higher-fidelity variant.
Links
Tags
LLM-jp-4-33B-thinking in the official 66.4 GB BF16 GGUF format. This variant preserves the original model precision for hosts with enough memory.
Links
Tags
IBM Granite 4.2 3B is a compact multilingual reasoning model for chat, coding, long-context tasks, and tool use. This entry uses the Q4_K_M GGUF; a higher-fidelity Q8_0 build is available as a variant.
Links
Tags
IBM Granite 4.2 3B in the higher-fidelity Q8_0 GGUF format. It is a compact multilingual reasoning model for chat, coding, and tool use.
Links
Tags
Repository: localaiLicense: apache-2.0
Carbon-3B is Hugging Face's 3B-parameter genomic foundation model for DNA and RNA sequence generation, recovery, variant-effect prediction, and motif-perturbation analysis. It supports 32,768 tokens natively and uses a hybrid tokenizer with 6-mer DNA tokens. This default entry uses the Q4_K_M GGUF. A higher-quality Q8_0 build is available as a variant. Prefix DNA sequences with `` and use uppercase A, C, G, and T characters in groups of six.
Links
Tags
Carbon-3B in the higher-quality Q8_0 GGUF format for genomic sequence generation and analysis.
Links
Tags
Repository: localaiLicense: mit
Ornith-1.5-35B-A3B is an MIT-licensed Qwen3.5 mixture-of-experts model from Ornith AI for agentic coding, reasoning, repository-level software tasks, and tool use. It supports text and image input with a context window of 262K tokens. This default entry uses the APEX Balanced GGUF and BF16 vision projector. Compact APEX and MTP-enabled APEX builds are available as variants.
Links
Tags
Ornith-1.5-35B-A3B in the smaller APEX Compact GGUF format, with the shared BF16 vision projector for multimodal prompts.
Links
Tags
Ornith-1.5-35B-A3B in the APEX Balanced GGUF format with native multi-token prediction enabled for speculative decoding, plus the shared BF16 vision projector.
Links
Tags
Ornith-1.5-35B-A3B in the APEX Compact GGUF format with native multi-token prediction enabled for speculative decoding, plus the shared BF16 vision projector.
Links
Tags
Repository: localaiLicense: mit
Ornith-1.5-35B-A3B is an MIT-licensed Qwen3.5 mixture-of-experts model from Ornith AI for agentic coding, reasoning, repository-level software tasks, and tool use. It activates about 3B parameters per token and supports text and image input with a context window of 262K tokens. This default entry uses the Q4_K_M GGUF and BF16 vision projector. A higher-quality Q8_0 model is available as a variant.
Links
Tags
Ornith-1.5-35B-A3B in the higher-quality Q8_0 GGUF format, with the shared BF16 vision projector for multimodal prompts.
Links
Tags
Tiel-Coder-35B-A3B is a 35B-parameter mixture-of-experts model for coding, reasoning, tool use, and vision tasks. This default entry uses the Q4_K_XL GGUF and BF16 vision projector.
Links
Tags
Tiel-Coder-35B-A3B in Q4_K_XL format with MTP speculative decoding and a BF16 vision projector.
Links
Tags
Tiel-Coder-35B-A3B in Q5_K_XL format with MTP speculative decoding and a BF16 vision projector.
Links
Tags
Tiel-Coder-35B-A3B in Q6_K_XL format with MTP speculative decoding and a BF16 vision projector.
Links
Tags
Tiel-Coder-35B-A3B in Q8_K_XL format with MTP speculative decoding and a BF16 vision projector.
Links
Tags
Tiel-Coder-35B-A3B in the higher-quality Q8_K_XL GGUF format, with the BF16 vision projector for multimodal prompts.
Links
Tags
Repository: localaiLicense: openmdw-1.1
NVIDIA Nemotron 3.5 Lightning is a text-only hybrid Mamba-2, attention, and mixture-of-experts model with 30B total parameters and 3B active parameters. It targets reasoning, coding, tool use, multilingual chat, and long-context agent workflows, with a context window of up to one million tokens. This entry uses the official Q4_K_M GGUF. Automatic variant selection can choose the smaller NVFP4 build or the higher-quality Q8_0 build when it fits.
Links
Tags
NVIDIA Nemotron 3.5 Lightning 30B-A3B in the official NVFP4 GGUF format. This is the smallest linked build and retains the model's reasoning, coding, tool-use, multilingual, and long-context capabilities.
Links
Tags
NVIDIA Nemotron 3.5 Lightning 30B-A3B in the official high-quality Q8_0 GGUF format for hosts with enough memory.
Links
Tags