Wilshire@lemmy.world to Technology@lemmy.worldEnglish · 4 months agoThe first GPT-4-class AI model anyone can download has arrived: Llama 405Barstechnica.comexternal-linkmessage-square56fedilinkarrow-up10arrow-down10
arrow-up10arrow-down1external-linkThe first GPT-4-class AI model anyone can download has arrived: Llama 405Barstechnica.comWilshire@lemmy.world to Technology@lemmy.worldEnglish · 4 months agomessage-square56fedilink
minus-squaresunzu@kbin.runlinkfedilinkarrow-up0·4 months ago405b ain’t running local unless you got a proepr set up is enterpise grade lol I think 70b is possible but I haven’t find anyone confirming it yet Also would like to know specs on whoever did it
minus-squareraldone01@lemmy.worldlinkfedilinkEnglisharrow-up0·4 months agoI regularly run llama3 70b unqantesized on two P40s and CPU at like 7tokens/s. It’s usable but not very fast.
minus-squaresunzu@kbin.runlinkfedilinkarrow-up0·4 months agoso there is no way a 24gb and 64gb can run thing?
minus-squareraldone01@lemmy.worldlinkfedilinkEnglisharrow-up0·4 months agoWhat are you asking exactly? What do you want to run? I assume you have a 24GB GPU and 64GB host RAM?
minus-squaresunzu@kbin.runlinkfedilinkarrow-up0·4 months agocorrect. and how ram speed work in this tbh
minus-squareraldone01@lemmy.worldlinkfedilinkEnglisharrow-up0·4 months agoMy memory sticks are all DDR4 with 32GB@2133MT/s.
minus-squareraldone01@lemmy.worldlinkfedilinkEnglisharrow-up0·edit-24 months agoMy specs because you asked: CPU: Intel(R) Xeon(R) E5-2699 v3 (72) @ 3.60 GHz GPU 1: NVIDIA Tesla P40 [Discrete] GPU 2: NVIDIA Tesla P40 [Discrete] GPU 3: Matrox Electronics Systems Ltd. MGA G200EH Memory: 66.75 GiB / 251.75 GiB (27%) Swap: 75.50 MiB / 40.00 GiB (0%)
minus-squaresunzu@kbin.runlinkfedilinkarrow-up0·4 months agook this is a server. 48gb cards and 67gb ram? for model alone?
minus-squareraldone01@lemmy.worldlinkfedilinkEnglisharrow-up0·4 months agoEach card has 24GB so 48GB vram total. I use ollama it fills whatever vrams is available on both cards and runs the rest on the CPU cores.
minus-squareVoyajer@lemmy.worldlinkfedilinkEnglisharrow-up0·edit-24 months agoI’ve run quantized 70B models on CPU with 32 gigs but it is very slow
minus-squarebizarroland@fedia.iolinkfedilinkarrow-up0·4 months agoI have a home server with 140 gigs of RAM, it was surprisingly cheap. It’s an HP z6 with the 6146 gold xeon processor. I found a seller who was selling it with a low spec silver and 16 gigs of RAM for like 250 bucks. Found the processor upgrade for about $120 and spend another $150 on 128gb of second-hand ECC ddr4. I think the total cost was something like $700 after throwing a couple of 8 TB hard drives in. I’ve also placed a Nvidia 4070 in it, which I got doing some horse trading. How close am I on the specs to being able to run the 70b version?
minus-squareBaroqueInMind@lemmy.onelinkfedilinkEnglisharrow-up0·4 months agoWhat’s the bus speed of the RAM? You might run it just find but still bottlenecked there.
minus-squaresunzu@kbin.runlinkfedilinkarrow-up0·4 months agoI gonna add some RAM with hope I can split original 70b between GPU and RAM. 8b is great what it is as is Looks like it should be possible, not sure how much performance hit offloading to RAM will do. Fafo
405b ain’t running local unless you got a proepr set up is enterpise grade lol
I think 70b is possible but I haven’t find anyone confirming it yet
Also would like to know specs on whoever did it
I regularly run llama3 70b unqantesized on two P40s and CPU at like 7tokens/s. It’s usable but not very fast.
so there is no way a 24gb and 64gb can run thing?
What are you asking exactly?
What do you want to run? I assume you have a 24GB GPU and 64GB host RAM?
correct. and how ram speed work in this tbh
My memory sticks are all DDR4 with 32GB@2133MT/s.
My specs because you asked:
CPU: Intel(R) Xeon(R) E5-2699 v3 (72) @ 3.60 GHz GPU 1: NVIDIA Tesla P40 [Discrete] GPU 2: NVIDIA Tesla P40 [Discrete] GPU 3: Matrox Electronics Systems Ltd. MGA G200EH Memory: 66.75 GiB / 251.75 GiB (27%) Swap: 75.50 MiB / 40.00 GiB (0%)ok this is a server. 48gb cards and 67gb ram? for model alone?
Each card has 24GB so 48GB vram total. I use ollama it fills whatever vrams is available on both cards and runs the rest on the CPU cores.
I’ve run quantized 70B models on CPU with 32 gigs but it is very slow
I have a home server with 140 gigs of RAM, it was surprisingly cheap. It’s an HP z6 with the 6146 gold xeon processor.
I found a seller who was selling it with a low spec silver and 16 gigs of RAM for like 250 bucks.
Found the processor upgrade for about $120 and spend another $150 on 128gb of second-hand ECC ddr4.
I think the total cost was something like $700 after throwing a couple of 8 TB hard drives in.
I’ve also placed a Nvidia 4070 in it, which I got doing some horse trading.
How close am I on the specs to being able to run the 70b version?
What’s the bus speed of the RAM? You might run it just find but still bottlenecked there.
It’s clocked at ddr4 2666
I gonna add some RAM with hope I can split original 70b between GPU and RAM. 8b is great what it is as is
Looks like it should be possible, not sure how much performance hit offloading to RAM will do. Fafo