Repository: localaiLicense: apache-2.0

Qwen3.8-27B in cdiamond's iMatrix-calibrated mixed-precision NVFP4 build. Selected attention and feed-forward tensors retain higher precision. Includes the F16 vision projector and enables the embedded MTP draft head with one draft token per step.
Links
Tags
Kujira's abliterated adaptation of Underdog Saluki 27B 1.0 uses mixed IQ2 weights with an embedded MTP head. This text-only llama.cpp build uses ordinary decoding; the MTP variant enables speculative decoding.
Links
Tags
Repository: localaiLicense: swift-open-license-1.0
Swift-Qwen3.8-27B is UkisAI's reasoning-efficient fine-tune of Qwen3.8-27B. The publisher reports 58.3% fewer thinking tokens with less than 1% quality loss. This Q4_K_M GGUF includes the F16 vision projector and enables MTP speculative decoding. The weights use the Swift Open License v1.0.
Links
Tags

Qwopus3.8-27B-Flash-V2 is a new post-training release for reasoning and agent workloads. This Q4_K_M GGUF includes the F32 vision projector and uses llama.cpp's embedded chat template with MTP speculative decoding.
Links
Tags

Qwopus3.8-27B-Flash-V2 is a new post-training release for reasoning and agent workloads. This Q8_0 GGUF includes the F32 vision projector and uses llama.cpp's embedded chat template with MTP speculative decoding.
Links
Tags
Repository: localaiLicense: apache-2.0

Qwopus3.8-27B-Flash is a Qwen3.8-27B fine-tune for reasoning and agent workloads. This Q4_K_M GGUF includes the F32 vision projector and uses llama.cpp's embedded chat template with MTP speculative decoding. The publisher reports a known Python code indentation issue.
Links
Tags
Repository: localaiLicense: apache-2.0

Qwopus3.8-27B-Flash is a Qwen3.8-27B fine-tune for reasoning and agent workloads. This Q8_0 GGUF includes the F32 vision projector and uses llama.cpp's embedded chat template with MTP speculative decoding. The publisher reports a known Python code indentation issue.
Links
Tags
Apodex-1.1-mini with MTP speculative decoding enabled on the recommended Q4_K_M GGUF. The model carries its native MTP head, so it needs no separate draft model. The F16 vision projector supports 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 UD-Q4_K_XL GGUF quantization and enables the model's MTP speculative-decoding head.
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
Repository: localaiLicense: apache-2.0
Dirk is a Qwen3.8 27B vision-language model with a concise chat template for agentic coding, reasoning, tool use, and general knowledge tasks. It preserves the model's MTP head for speculative decoding and supports a 262K-token context window. This default entry uses the Q4_K_XL GGUF and F16 vision projector. A choice of Q5_K_XL, Q6_K_XL, and Q8_K_XL builds is available through variants.
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
Dirk in the higher-quality Q5_K_XL GGUF format, with MTP speculative decoding and the shared F16 vision projector for multimodal prompts.
Links
Tags
Dirk in the higher-quality Q6_K_XL GGUF format, with MTP speculative decoding and the shared F16 vision projector for multimodal prompts.
Links
Tags
Repository: localaiLicense: apache-2.0
Qwen3.8-27B-Uncensored reduces refusal behavior while retaining the base model's text, vision, reasoning, and tool-use capabilities. Its integrated MTP head supports speculative decoding without a separate draft model. This default entry uses the Q4_K_M GGUF and F16 vision projector. A higher-quality Q8_0 model is available as a variant.
Links
Tags
Repository: localaiLicense: apache-2.0

Huihui Qwen3.8 27B is an abliterated vision-language model published by huihui-ai. This BF16 GGUF build includes the shared BF16 vision projector and enables MTP speculative decoding through llama.cpp. Q4_K, Q5_K, Q6_K, and Q8_0 variants are available as smaller downloads.
Links
Tags

Huihui Qwen3.8 27B in Q4_K GGUF format, with the shared BF16 vision projector and MTP speculative decoding through llama.cpp.
Links
Tags

Huihui Qwen3.8 27B in Q5_K GGUF format, with the shared BF16 vision projector and MTP speculative decoding through llama.cpp.
Links
Tags

Huihui Qwen3.8 27B in Q6_K GGUF format, with the shared BF16 vision projector and MTP speculative decoding through llama.cpp.
Links
Tags

Huihui Qwen3.8 27B in Q8_0 GGUF format, with the shared BF16 vision projector and MTP speculative decoding through llama.cpp.
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