eicker@lemmy.world to Technology@lemmy.worldEnglish · 13 days agoOpenAI Hoarding Tens Of Thousands Of Apple Mac mini And Mac Studio Devices, As ASUS And MSI Burn Through Their Entire First Batch Of NVIDIA RTX Spark Chip And Beg For More.wccftech.comexternal-linkmessage-square64linkfedilinkarrow-up1101arrow-down10
arrow-up1101arrow-down1external-linkOpenAI Hoarding Tens Of Thousands Of Apple Mac mini And Mac Studio Devices, As ASUS And MSI Burn Through Their Entire First Batch Of NVIDIA RTX Spark Chip And Beg For More.wccftech.comeicker@lemmy.world to Technology@lemmy.worldEnglish · 13 days agomessage-square64linkfedilink
minus-squareChee_Koala@lemmy.worldlinkfedilinkEnglisharrow-up0·edit-213 days agoAny 27b Model you can currently recommend for a 16gb AMD ? Mostly coding tasks but not exclusively.
minus-squaredeleted@lemmy.worldlinkfedilinkEnglisharrow-up0·12 days agoFor your hardware, the VRam is not enough to run 27b but, I’d recommend Qwen 3.5 9b for image / text to text. And I’m planning to experiment with Qwen 3.8 9b for text to text. 4_k_m quantization is the sweet spot for performance and ram usage. Also, I find Llama cpp is better than Ollama in terms of performance.
minus-squaremierdabird@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up0·13 days ago9060xt 16gb is the most cost effective new GPU, but if you’re going used look for a V620 on eBay. It’s a 6800xt chip but in server form factor GPU with 32GB vram. Can be a bit of a pain to set up but by far the most cost effective option IMO
minus-squareDarkaga@lemmy.worldlinkfedilinkEnglisharrow-up0·12 days agoV620s were a good deal when you could get them for $350, now they’re $700+ and no longer a good deal.
Any 27b Model you can currently recommend for a 16gb AMD ? Mostly coding tasks but not exclusively.
For your hardware, the VRam is not enough to run 27b but, I’d recommend Qwen 3.5 9b for image / text to text.
And I’m planning to experiment with Qwen 3.8 9b for text to text.
4_k_m quantization is the sweet spot for performance and ram usage.
Also, I find Llama cpp is better than Ollama in terms of performance.
9060xt 16gb is the most cost effective new GPU, but if you’re going used look for a V620 on eBay. It’s a 6800xt chip but in server form factor GPU with 32GB vram. Can be a bit of a pain to set up but by far the most cost effective option IMO
V620s were a good deal when you could get them for $350, now they’re $700+ and no longer a good deal.