zralddeepseekv4.1
> 📖 Research White Paper: 📄 Read Whitepaper (PDF) | 🌐 View Online | 📝 Full MI300X Serving...
> 📖 Research White Paper: 📄 Read Whitepaper (PDF) | 🌐 View Online | 📝 Full MI300X Serving...
Independently computed using dedicated cloud compute clusters, funded 100% out-of-pocket. If you consider these releases to be of...
oQ4e-quantized MLX build (created by xunlinkx with the omlx pipeline) of Mondk/Spark-X2.5-4B-Abliterated-Uncensored for first-class, all-local serving on Apple...
8 quantizations. One CPU setup. Quality, file size and throughput in the same record. Reading the table: Q80/Q6K...
A sub-4-bit routed-expert quantization of Qwen/Qwen3.8-Flash-Next, built to fit the full 262,144-token context of a 125B-A6B multimodal MoE...
Standard static quants (no imatrix) + APEX mixed-precision quants of SC117’s abliterix v6 trial 21 merge. Original model:...
WAL-Ternary-8B V77 is an independently constructed low-bit version of Qwen/Qwen3-8B. The complete checkpoint occupies 2.898417 bits per original...
12,87 ГБ, один файл, mmap-run — и 105 токенов/с декодируются на одной карте. Транскодирование EschaLabs/Qwen3.6-35B-A3B-Escha-W2 в контейнер CMF,...
ROCmFP4 Strix-Lean quant of mistralai/Leanstral-1.5-119B-A6B for AMD Radeon / Ryzen AI Max+ (gfx1151) inference via the public charlie12345/ROCmFPX...
A 295B-A21B MoE served on one 128 GB DGX Spark at 2.9 bits per parameter, through stock vLLM...