Ternary-Bonsai-2-27B-ROCm-gfx1151
This repository contains no weights. It documents running prism-ml/Ternary-Bonsai-2-27B-gguf on ROCm, which its model card does not cover...
This repository contains no weights. It documents running prism-ml/Ternary-Bonsai-2-27B-gguf on ROCm, which its model card does not cover...
4-bit ROCmFP4 quantizations of XingChen-AGI/Xing4.0-29B-A4B, China Telecom AI’s 29B-total / 4B-active MoE (formerly the TeleChat series), built for...
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...
🧠 LFM 2.5 8B ThinkingCap — GGUF — Тонкая настройка: ThinkingCap SFT Модальности:Генерация текста Области применения:Логика и рассуждение...
4-разрядный квант ROCmFP4STRIX Kwaipilot/KAT-Coder-V2.5-Dev с головкой MTP (многотокенного предсказания) модели, привитой обратно в Q80, чтобы он мог самоспецифицироваться....
ROCmFP4 and ROCmFPX quantizations of MiMo-V2.5 (310B total / 15B active MoE), built for AMD Strix Halo (Ryzen...
A local AI team, built around AMD Strix Halo. Ornith1.5 Ciru Halo Agent combines a custom quantization of...
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...
Qwen3.8-27B — the dense hybrid-attention Qwen release (48 gated-delta-net layers + 16 full-attention layers, fullattentioninterval = 4, native...
A 4-bit ROCmFP4STRIX` quant of poolside/Laguna-S-2.1 (118B-A8B), built and measured on an AMD Ryzen AI Max+ 395 (Strix...