← Back to context Comment by madduci 5 months ago VRAM, not RAM. I wish it was light enough for iGPUs too 3 comments madduci Reply KiwiJohnno 5 months ago I ran the 26B model on my i5 which has no discrete graphics card. It ran about 7 tokens/sec, and appreared to be a very capable model. madduci 5 months ago I've tested the e4B with the iGPU and it works incredibly good locally. I'll try this model as soon as it is available on ollama madduci 5 months ago Interesting, thanks for the feedback!
KiwiJohnno 5 months ago I ran the 26B model on my i5 which has no discrete graphics card. It ran about 7 tokens/sec, and appreared to be a very capable model. madduci 5 months ago I've tested the e4B with the iGPU and it works incredibly good locally. I'll try this model as soon as it is available on ollama madduci 5 months ago Interesting, thanks for the feedback!
madduci 5 months ago I've tested the e4B with the iGPU and it works incredibly good locally. I'll try this model as soon as it is available on ollama
I ran the 26B model on my i5 which has no discrete graphics card. It ran about 7 tokens/sec, and appreared to be a very capable model.
I've tested the e4B with the iGPU and it works incredibly good locally. I'll try this model as soon as it is available on ollama
Interesting, thanks for the feedback!