DEV Community

#mixtureofexperts

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
One billion fire, eight billion sit in memory
randomchaos profile
RC

One billion fire, eight billion sit in memory

#mixtureofexperts #edgeai #ondevicellm
Comments
3 min read
FreeToken: Run Frontier MoE Models on Your Own GPU, and the RAM It Takes
itxtayab profile

FreeToken: Run Frontier MoE Models on Your Own GPU, and the RAM It Takes

#opensource #localllm #mixtureofexperts #llminference
Comments
9 min read
Extending llama.cpp to Support Reflection Beam-1.0-501B-A23B: Handling Complex MoE and Attention Architectures
pdrojack profile

Extending llama.cpp to Support Reflection Beam-1.0-501B-A23B: Handling Complex MoE and Attention Architectures

#llamacpp #mixtureofexperts #attention #modelconversion
Comments
3 min read
Addestrare un mini-LLM da 25M parametri su CPU: anatomia di un GLM “flash” e cosa imparare davvero
frontendfacile profile

Addestrare un mini-LLM da 25M parametri su CPU: anatomia di un GLM “flash” e cosa imparare davvero

#llmsucpu #attenzionesparsa #attenzionelineare #mixtureofexperts
Comments
5 min read
Checking a Cost Model Against a Stranger's Config File
megapixel99 profile

Checking a Cost Model Against a Stranger's Config File

#llm #measurement #mixtureofexperts
1
Comments
5 min read
Qwen3.8-Flash-Next vs Qwen3.8-27B: 125B Parameters, 6B Active — What the Qwen4 Preview Changes
shaam_ai profile

Qwen3.8-Flash-Next vs Qwen3.8-27B: 125B Parameters, 6B Active — What the Qwen4 Preview Changes

#qwen #openweightllm #mixtureofexperts #aiagents
Comments
6 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
⌂ 换网址