Qwen3.8-27B-Uncensored-exl3-4bpw
EXL3 квантование orcarouter/Qwen3.8-27B-Uncensored, аблитерированная (отказ-удаленная) сборка Qwen/Qwen3.8-27B. 16 ГБ на диске — подходит для одной карты 24 ГБ...
Метка: mtp
GLM-5.3-Flash-Spark-Q2XL-MTP
Spark is a quality-first 2.80 BPW GGUF quant of zai-org/GLM-5.3-Flash, tuned to fit and run fully on a...
grug-v1.1-qwen-3.8-27b-mtp
same grug as ProCreations/grug-v1.1-qwen-3.8-27b, plus a draft head that guess ahead, tuned on grug own output. Qwen3.8 ship...
Qwen3.8-27B-MTP-Q4_0_ROCMFP4_STRIX_LEAN
Qwen3.8-27B — the dense hybrid-attention Qwen release (48 gated-delta-net layers + 16 full-attention layers, fullattentioninterval = 4, native...
NVIDIA-Nemotron-Labs-Teacher-Instruction-Following
The post-training data has a cutoff date of May 2026. The pre-training data has a cutoff date of...
Qwen3.6-40B-Fable-Fusion-6-Core-Deckard-Eleanor-Heretic-Uncensored-W4A16-AutoRound
4-bit weight-only quantization (W4A16) of DavidAU’s 40B «Chimera» — the 6-Core Fable Fusion Heretic Uncensored model. Quantized with...
Qwen3.6-27B-Architect-Polaris2-Fable-B-F451-MTP-ROCmFPX-GGUF
Text-only ROCmFPX/ROCmFP4 GGUF builds of nightmedia/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451, with the checkpoint’s embedded one-layer MTP draft model preserved. These are experimental...
DeepSeek-V4-Flash-MTP-GGUF
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...
Qwen3.6-35B-A3B-NVFP4-MTP-GGUF
RTX 5090 Windows native GGUF comparison — updated July 19, 2026 Native llama.cpp conversions of NVIDIA and Unsloth...
Qwopus3.6-27B-Coder-MTPLX-4bit-Speed
Первая сборка MTPLX Qwopus3.6-27B-Coder — тонкая настройка агентного кодирования Jackrong Qwopus3.6-27B-v2 (репо-уровневое кодирование, многооборотная оркестровка инструмента, 67,0% SWE-bench...