Hardware guide · Olmo
OL What hardware do you need to run Olmo 3 7B Instruct?
Olmo 3 7B Instruct needs about 5.6 GB to run at Q4_K_M, so the lightest hardware that runs it is Nvidia GeForce RTX 3060 Ti (8GB). 35 of 43 devices tested can run it.
- Needs (Q4_K_M)
- ~5.6 GB
- Devices that run it
- 35
- Too small
- 8
- Lightest that runs it
- ~7 GB
Recommended Q4_K_M
Runs at Q4_K_M using ~5.6 GB of ~7 GB usable.
What kind of hardware runs Olmo 3 7B Instruct
Of the 35 devices that run it, here is the split by hardware class.
11 discrete GPUs 13 Macs 2 laptops 9 phones
Hardware that runs Olmo 3 7B Instruct
Ranked by usable memory, lightest first. Prices are approximate street prices for the device itself (a GPU is the card alone; a Mac is the whole machine). Tok/s is a bandwidth estimate; see methodology.
Compatible devices 35 total
- YesNvidia GeForce RTX 3060 Ti (8GB) from $399~7 GB usable · uses ~5.6 GB · ~70 tok/s est.
- YesNvidia GeForce GTX 1070 (8GB) from $379~7 GB usable · uses ~5.6 GB · ~40 tok/s est.
- YesiPhone 17 Pro from $1,099~8 GB usable · uses ~5.6 GB · ~9 tok/s est.
- YesiPhone Air from $999~8 GB usable · uses ~5.6 GB · ~9 tok/s est.
- YesSamsung Galaxy S24 Ultra from $1,299~8.5 GB usable · uses ~5.6 GB · ~9 tok/s est.
- YesGeneric Android Phone (12GB RAM)~8.5 GB usable · uses ~5.6 GB
- YesApple M2 (16GB) from $1,199~10.5 GB usable · uses ~5.6 GB · ~19 tok/s est.
- YesApple M4 (16GB) from $999~10.5 GB usable · uses ~5.6 GB · ~23 tok/s est.
- YesGoogle Pixel 9 Pro from $999~10.5 GB usable · uses ~5.6 GB · ~8 tok/s est.
- YesApple M5 (16GB) from $1,099~10.5 GB usable · uses ~5.6 GB · ~29 tok/s est.
- YesGoogle Pixel 10 Pro from $999~10.5 GB usable · uses ~5.6 GB · ~8 tok/s est.
- YesNvidia GeForce RTX 3060 (12GB) from $329~11 GB usable · uses ~5.6 GB · ~56 tok/s est.
- YesNvidia GeForce RTX 4070 (12GB) from $599~11 GB usable · uses ~5.6 GB · ~79 tok/s est.
- YesApple M3 Pro (18GB) from $1,299~12 GB usable · uses ~5.6 GB · ~19 tok/s est.
- Yes16GB RAM Laptop (CPU/iGPU only) from $750~12 GB usable · uses ~5.6 GB · ~11 tok/s est.
- YesiPad Pro M4 (16GB, 1TB/2TB config) from $1,599~12 GB usable · uses ~5.6 GB · ~14 tok/s est.
- YesSamsung Galaxy S25 Ultra (16GB, 1TB config only) from $1,619~12 GB usable · uses ~5.6 GB · ~10 tok/s est.
- YesSamsung Galaxy S26 Ultra (16GB, 1TB config) from $1,299~12 GB usable · uses ~5.6 GB · ~10 tok/s est.
- YesNvidia GeForce RTX 4060 Ti (16GB) from $499~15 GB usable · uses ~5.6 GB · ~45 tok/s est.
- YesNvidia GeForce RTX 4080 (16GB) from $1,199~15 GB usable · uses ~5.6 GB · ~112 tok/s est.
- YesApple M4 (24GB) from $1,299~16 GB usable · uses ~5.6 GB · ~23 tok/s est.
- YesApple M4 Pro (24GB) from $1,999~16 GB usable · uses ~5.6 GB · ~53 tok/s est.
- YesApple M5 (32GB) from $1,299~21 GB usable · uses ~5.6 GB · ~29 tok/s est.
- YesNvidia GeForce RTX 4090 (24GB) from $1,599~23 GB usable · uses ~5.6 GB · ~158 tok/s est.
- YesNvidia GeForce RTX 3090 (24GB) from $1,499~23 GB usable · uses ~5.6 GB · ~146 tok/s est.
- YesAMD Radeon RX 7900 XTX (24GB) from $999~23 GB usable · uses ~5.6 GB · ~150 tok/s est.
- Yes32GB RAM Laptop (CPU/iGPU only) from $1,100~28 GB usable · uses ~5.6 GB · ~11 tok/s est.
- YesNvidia GeForce RTX 5090 (32GB) from $1,999~31 GB usable · uses ~5.6 GB · ~280 tok/s est.
- YesApple M4 Pro (48GB) from $2,399~32 GB usable · uses ~5.6 GB · ~53 tok/s est.
- YesApple M5 Pro (48GB) from $2,199~32 GB usable · uses ~5.6 GB · ~59 tok/s est.
- YesApple M4 Max (64GB) from $3,499~48 GB usable · uses ~5.6 GB · ~105 tok/s est.
- YesApple M4 Max (128GB) from $3,499~96 GB usable · uses ~5.6 GB · ~105 tok/s est.
- YesAMD Ryzen AI Halo (128GB) from $3,999~96 GB usable · uses ~5.6 GB · ~40 tok/s est.
- YesApple M5 Max (128GB) from $3,599~96 GB usable · uses ~5.6 GB · ~118 tok/s est.
- YesApple M3 Ultra (256GB) from $3,999~192 GB usable · uses ~5.6 GB · ~158 tok/s est.
Too small for Olmo 3 7B Instruct
See the full Olmo 3 7B Instruct memory breakdown, or compare it against other models.
Sources
Memory at Q4_K_M (5.6 GB = 4.16 GB weights + KV cache + overhead), validated 2026-09-07. See methodology.