minus-squarepepperfree@sh.itjust.workstoLocalLLaMA@sh.itjust.works•Mistral Says Its AI Model ‘Le Chonk’ Has Leapfrogged China in the Open-Weight Race (1T-A52B)linkfedilinkEnglisharrow-up4·12 days agoThey host deepseek 4.1 flash and glm 5.3 you know. So mistral making LLM and hosting other LLM linkfedilink
minus-squarepepperfree@sh.itjust.workstoLocalLLaMA@sh.itjust.works•KV Cache Quantization Benchmarks for Long ContextlinkfedilinkEnglisharrow-up1·12 days agoIs tcq better than kvarn? linkfedilink
minus-squarepepperfree@sh.itjust.workstoLocalLLaMA@sh.itjust.works•JEV collection(zero-shot decision model) SHARE list of links HFlinkfedilinkEnglisharrow-up1·1 month agoWhat’s this 🤣 https://huggingface.co/richardyoung/Bev-9B-inverted linkfedilink
pepperfree@sh.itjust.works to LocalLLaMA@sh.itjust.worksEnglish · 2 months agoQwen3.8 27B prefiller from ISTA-DASLabplus-squarehuggingface.coexternal-linkmessage-square0linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkQwen3.8 27B prefiller from ISTA-DASLabplus-squarehuggingface.copepperfree@sh.itjust.works to LocalLLaMA@sh.itjust.worksEnglish · 2 months agomessage-square0linkfedilink
They host deepseek 4.1 flash and glm 5.3 you know. So mistral making LLM and hosting other LLM