GLM-5.3-Flash with a run-time refusal vector: EXL3 2.05 bpw, an EXL3 2/3-bit mix and Maya-M. Measured on 4x RTX 3090.
superalesha
alesha-pro
P(doom) 1%
AI & ML interests
None yet
Recent Activity
updated a collection 1 day ago
GLM-5.3-Flash on 4x RTX 3090 updated a collection 1 day ago
GLM-5.3-Flash on 4x RTX 3090 updated a collection 1 day ago
GLM-5.3-Flash on 4x RTX 3090Organizations
None yet
EXL3 HQ quants with the Huihui edit in the weights, and ISTA-DASLab GSQ-RCO GGUFs with the same direction as a Strata control vector.
-
alesha-pro/Huihui-Qwen3.8-Flash-Next-abliterated-exl3-3bit-hq_h6_ng6
Image-Text-to-Text • 26B • Updated • 214 • 1 -
alesha-pro/Huihui-Qwen3.8-Flash-Next-abliterated-exl3-4bit-hq_h6_ng6
Image-Text-to-Text • 34B • Updated • 124 • 4 -
alesha-pro/Huihui-Qwen3.8-Flash-Next-abliterated-exl3-5bit-hq_h6_ng6
Image-Text-to-Text • 42B • Updated • 66 • 1 -
alesha-pro/Qwen3.8-Flash-Next-abliterated-GSQ-RCO-Strata-GGUF
Image-Text-to-Text • 120k • Updated • 83.2k • 100
GLM-5.3-Flash with a run-time refusal vector: EXL3 2.05 bpw, an EXL3 2/3-bit mix and Maya-M. Measured on 4x RTX 3090.
EXL3 HQ quants with the Huihui edit in the weights, and ISTA-DASLab GSQ-RCO GGUFs with the same direction as a Strata control vector.
-
alesha-pro/Huihui-Qwen3.8-Flash-Next-abliterated-exl3-3bit-hq_h6_ng6
Image-Text-to-Text • 26B • Updated • 214 • 1 -
alesha-pro/Huihui-Qwen3.8-Flash-Next-abliterated-exl3-4bit-hq_h6_ng6
Image-Text-to-Text • 34B • Updated • 124 • 4 -
alesha-pro/Huihui-Qwen3.8-Flash-Next-abliterated-exl3-5bit-hq_h6_ng6
Image-Text-to-Text • 42B • Updated • 66 • 1 -
alesha-pro/Qwen3.8-Flash-Next-abliterated-GSQ-RCO-Strata-GGUF
Image-Text-to-Text • 120k • Updated • 83.2k • 100
models 11
alesha-pro/GLM-5.3-Flash-abliterated-exl3-2.4bpw-mix
Image-Text-to-Text • 49B • Updated • 36 • 2
alesha-pro/GLM-5.3-Flash-abliterated-exl3-2.05bpw
Image-Text-to-Text • 43B • Updated • 26 • 2
alesha-pro/GLM-5.3-Flash-abliterated-Maya-M-GGUF
Image-Text-to-Text • Updated • 678 • 1
alesha-pro/Qwen3.8-Flash-Next-abliterated-GSQ-RCO-Coder-Strata-GGUF
Image-Text-to-Text • 120k • Updated • 5.04k • 2
alesha-pro/Qwen3.8-27B-S-mirai-GGUF
Text Generation • 323k • Updated • 6.96k • 47
alesha-pro/Qwen3.8-Flash-Next-abliterated-GSQ-RCO-Strata-GGUF
Image-Text-to-Text • 120k • Updated • 83.2k • 100
alesha-pro/Huihui-Qwen3.8-Flash-Next-abliterated-exl3-5bit-hq_h6_ng6
Image-Text-to-Text • 42B • Updated • 66 • 1
alesha-pro/Huihui-Qwen3.8-Flash-Next-abliterated-exl3-3bit-hq_h6_ng6
Image-Text-to-Text • 26B • Updated • 214 • 1
alesha-pro/Huihui-Qwen3.8-Flash-Next-abliterated-exl3-4bit-hq_h6_ng6
Image-Text-to-Text • 34B • Updated • 124 • 4
alesha-pro/vllm-cross-model-kv
Updated • 1