GLM-4.7-Flash-RAZOR-17B-A3B-E32of64
GLM-4.7-Flash with half of its routed experts removed by RAZOR, a training-free expert pruning method. Every MoE layer...
GLM-4.7-Flash with half of its routed experts removed by RAZOR, a training-free expert pruning method. Every MoE layer...
> Бесплатная публичная загрузка: Blackfrost-Research/GLM-5.3-DERISKED-NVFP4-V2. Для загрузки весов не требуется оплата, вход в систему или запрос на доступ....
This is an exllamav3 quantization of orcarouter’s GLM-5.3-Flash-Uncensored-FP8. Quantized targeting 2.5 bpw with the -hq option to get...
W4AFP8 quantization of zai-org/GLM-5.3-Flash: routed MoE expert weights in INT4 (group-128, symmetric, AWQ-calibrated) with static per-tensor FP8 activation...
> ⚠️ Content warning. This model has had the base model’s refusal behavior > suppressed. It will comply...
— Model Architecture: GLM-5.3-Flash — Input: Text, Image — Output: Text — Model Optimizations: — Weight quantization: INT4...
Сообщество GGUF проекта модели DFlash 2 от Inco AI для GLM-5.3-Flash. Это не самостоятельная языковая модель. Он только...
Сообщество NVIDIA ModelOpt NVFP4 Z.ai GLM-5.3-Flash с использованием ОДНОЙ DGX Spark. Экспертами по слоям 3–44 являются NVFP4. MTP...
GLM-4.7-Flash-Abliteratex is a rebuilt successor to wangzhang/GLM-4.7-Flash-abliterated. The release focuses on preserving the official checkpoint structure, reducing collateral...
> A 34%-expert-pruned GLM-5.2 that holds parity with the full unpruned model on a > well-powered real-world eval...