QWEN-3.8-MAX-DERISKED Blackfrost-Research/Qwen3.8-2.4T-A95B-DERISKED-FP8 Text Generation • 2.4T • Updated Aug 14
GLM-5.2 — De-Risked 753B MoE. In-house de-risking applied directly to the zai-org/GLM-5.2 full-precision source, not to a third-party quantization. The-freezer/GLM-5.2-DERISKED-BF16 Text Generation • 743B • Updated Aug 24 • 1 The-freezer/GLM-5.2-DERISKED-NVFP4 Text Generation • 386B • Updated Aug 13 • 2 The-freezer/GLM-5.2-DERISKED-REAP-NU176-NVFP4 Text Generation • 273B • Updated Aug 13
Kimi K3 — De-Risked 2.8T LatentMoE + KDA, refusal-surface reduced at the weight level (ABLITERATED). GGUF variants need llama.cpp PR #26185 — mainline cannot load them. Blackfrost-Research/KIMI-K3-DERISKED-MXFP4-GGUF Text Generation • 2.8T • Updated Aug 24 • 1 Blackfrost-AI/KIMI-K3-Q2_K-GGUF-ABLITERATED Text Generation • 2.8T • Updated Aug 4 • 323 • 15
QWEN-3.8-MAX-DERISKED Blackfrost-Research/Qwen3.8-2.4T-A95B-DERISKED-FP8 Text Generation • 2.4T • Updated Aug 14
Kimi K3 — De-Risked 2.8T LatentMoE + KDA, refusal-surface reduced at the weight level (ABLITERATED). GGUF variants need llama.cpp PR #26185 — mainline cannot load them. Blackfrost-Research/KIMI-K3-DERISKED-MXFP4-GGUF Text Generation • 2.8T • Updated Aug 24 • 1 Blackfrost-AI/KIMI-K3-Q2_K-GGUF-ABLITERATED Text Generation • 2.8T • Updated Aug 4 • 323 • 15
GLM-5.2 — De-Risked 753B MoE. In-house de-risking applied directly to the zai-org/GLM-5.2 full-precision source, not to a third-party quantization. The-freezer/GLM-5.2-DERISKED-BF16 Text Generation • 743B • Updated Aug 24 • 1 The-freezer/GLM-5.2-DERISKED-NVFP4 Text Generation • 386B • Updated Aug 13 • 2 The-freezer/GLM-5.2-DERISKED-REAP-NU176-NVFP4 Text Generation • 273B • Updated Aug 13
