Discover and install AI models from our curated collection
Apodex-1.1-mini in the higher-quality Q8_0 GGUF format, with the shared F16 vision projector for multimodal prompts.
Links
Tags
Repository: localaiLicense: mit
GLM-5.3-Flash is Z.ai's natively multimodal 320B-parameter mixture-of-experts model with 18B active parameters. It combines sparse and linear attention for coding, agentic work, tool use, vision, and long-context tasks. This entry uses the higher-quality Q8_0 GGUF quantization and enables the model's MTP speculative-decoding head.
Links
Tags

Qwen3.8-Flash-Next in the higher-quality Q8_0 GGUF format, with the shared BF16 vision projector. This build preserves more model quality but needs more memory than the default Q4 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
IBM Granite 4.2 8B in the higher-fidelity Q8_0 GGUF format. It is a multilingual reasoning model for chat, coding, and tool use.
Links
Tags
IBM Granite 4.2 30B in the higher-fidelity Q8_0 GGUF format. It is the family's flagship multilingual reasoning model for chat, coding, and tool use.
Links
Tags
Dirk in the higher-quality Q8_K_XL GGUF format, with MTP speculative decoding and the shared F16 vision projector for multimodal prompts.
Links
Tags
Hy-MT2-1.8B in the higher-quality 1.9 GB Q8_0 GGUF format. This variant preserves more model fidelity for hosts with enough memory.
Links
Tags
Carbon-3B in the higher-quality Q8_0 GGUF format for genomic sequence generation and analysis.
Links
Tags
Carbon-8B in the higher-quality Q8_0 GGUF format for genomic sequence generation and analysis.
Links
Tags
Ornith-1.0-9B in the higher-quality Q8_0 GGUF format, with the shared F16 vision projector for multimodal prompts.
Links
Tags
Ornith-1.5-9B in the higher-quality Q8_0 GGUF format, with the shared BF16 vision projector for multimodal prompts.
Links
Tags
Ornith-1.5-9B OBLITERATED in the higher-quality Q8_0 GGUF format, with the shared BF16 vision projector. Its safety guardrails are removed, and the publisher recommends this quantization for better behavior fidelity.
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
Thomson-1.0-Small in the higher-quality Q8_0 GGUF format, with the shared BF16 vision projector for multimodal prompts.
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
Ornith-1.5-397B in the higher-quality Q8_0 GGUF format, with the shared BF16 vision projector for multimodal prompts.
Links
Tags

Qwen3.8-27B OBLITERATED in the higher-quality Q8_0 GGUF format. This model is modified for refusal-removal and red-team research, and its safety guardrails have been removed.
Links
Tags

Qwen3.8-27B in the official Q8_0 GGUF format. This variant provides higher model fidelity for hosts with enough memory.
Links
Tags

Qwen3.8-9B in the higher-quality Q8_0 GGUF format. This variant preserves more model fidelity for hosts with enough memory.
Links
Tags

Qwen3.8-4B in the higher-quality Q8_0 GGUF format. This variant preserves more model fidelity for hosts with enough memory.
Links
Tags