Hardware guide · Nemotron
NE What hardware do you need to run Nemotron Nano 9B v2?
Nemotron Nano 9B v2 needs about 7.6 GB to run at Q4_K_M, so the lightest hardware that runs it is iPhone 17 Pro. 39 of 49 devices tested can run it.
- Needs (Q4_K_M)
- ~7.6 GB
- Devices that run it
- 39
- Too small
- 10
- Lightest that runs it
- ~8 GB
Recommended Q4_K_M
Apple M2 (16GB) Yes
Runs at Q4_K_M using ~7.6 GB of ~10.5 GB usable. You have room for Q8_0 for higher quality.
What kind of hardware runs Nemotron Nano 9B v2
Of the 39 devices that run it, here is the split by hardware class.
15 discrete GPUs 13 Macs 2 laptops 9 phones
Hardware that runs Nemotron Nano 9B v2
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 39 total
- TightiPhone 17 Pro from $1,099~8 GB usable · uses ~7.6 GB · ~6 tok/s est.
- TightiPhone Air from $999~8 GB usable · uses ~7.6 GB · ~6 tok/s est.
- TightSamsung Galaxy S24 Ultra from $1,299~8.5 GB usable · uses ~7.6 GB · ~6 tok/s est.
- TightGeneric Android Phone (12GB RAM)~8.5 GB usable · uses ~7.6 GB
- YesApple M2 (16GB) from $1,199~10.5 GB usable · uses ~7.6 GB · ~13 tok/s est.
- YesApple M4 (16GB) from $999~10.5 GB usable · uses ~7.6 GB · ~16 tok/s est.
- YesGoogle Pixel 9 Pro from $999~10.5 GB usable · uses ~7.6 GB · ~6 tok/s est.
- YesApple M5 (16GB) from $1,099~10.5 GB usable · uses ~7.6 GB · ~20 tok/s est.
- YesGoogle Pixel 10 Pro from $999~10.5 GB usable · uses ~7.6 GB · ~6 tok/s est.
- YesNvidia GeForce RTX 3060 (12GB) from $329~11 GB usable · uses ~7.6 GB · ~38 tok/s est.
- YesNvidia GeForce RTX 4070 (12GB) from $599~11 GB usable · uses ~7.6 GB · ~54 tok/s est.
- YesNvidia GeForce RTX 5070 (12GB) from $549~11 GB usable · uses ~7.6 GB · ~72 tok/s est.
- YesApple M3 Pro (18GB) from $1,299~12 GB usable · uses ~7.6 GB · ~13 tok/s est.
- Yes16GB RAM Laptop (CPU/iGPU only) from $750~12 GB usable · uses ~7.6 GB · ~7 tok/s est.
- YesiPad Pro M4 (16GB, 1TB/2TB config) from $1,599~12 GB usable · uses ~7.6 GB · ~10 tok/s est.
- YesSamsung Galaxy S25 Ultra (16GB, 1TB config only) from $1,619~12 GB usable · uses ~7.6 GB · ~7 tok/s est.
- YesSamsung Galaxy S26 Ultra (16GB, 1TB config) from $1,299~12 GB usable · uses ~7.6 GB · ~7 tok/s est.
- YesNvidia GeForce RTX 4060 Ti (16GB) from $499~15 GB usable · uses ~7.6 GB · ~31 tok/s est.
- YesNvidia GeForce RTX 4080 (16GB) from $1,199~15 GB usable · uses ~7.6 GB · ~77 tok/s est.
- YesNvidia GeForce RTX 5080 (16GB) from $999~15 GB usable · uses ~7.6 GB · ~103 tok/s est.
- YesNvidia GeForce RTX 5070 Ti (16GB) from $749~15 GB usable · uses ~7.6 GB · ~96 tok/s est.
- YesNvidia GeForce RTX 5060 Ti (16GB) from $429~15 GB usable · uses ~7.6 GB · ~48 tok/s est.
- YesAMD Radeon RX 9070 XT (16GB) from $599~15 GB usable · uses ~7.6 GB · ~68 tok/s est.
- YesApple M4 (24GB) from $1,299~16 GB usable · uses ~7.6 GB · ~16 tok/s est.
- YesApple M4 Pro (24GB) from $1,999~16 GB usable · uses ~7.6 GB · ~36 tok/s est.
- YesApple M5 (32GB) from $1,299~21 GB usable · uses ~7.6 GB · ~20 tok/s est.
- YesNvidia GeForce RTX 4090 (24GB) from $1,599~23 GB usable · uses ~7.6 GB · ~108 tok/s est.
- YesNvidia GeForce RTX 3090 (24GB) from $1,499~23 GB usable · uses ~7.6 GB · ~100 tok/s est.
- YesAMD Radeon RX 7900 XTX (24GB) from $999~23 GB usable · uses ~7.6 GB · ~103 tok/s est.
- Yes32GB RAM Laptop (CPU/iGPU only) from $1,100~28 GB usable · uses ~7.6 GB · ~7 tok/s est.
- YesNvidia GeForce RTX 5090 (32GB) from $1,999~31 GB usable · uses ~7.6 GB · ~192 tok/s est.
- YesApple M4 Pro (48GB) from $2,399~32 GB usable · uses ~7.6 GB · ~36 tok/s est.
- YesApple M5 Pro (48GB) from $2,199~32 GB usable · uses ~7.6 GB · ~40 tok/s est.
- YesApple M4 Max (64GB) from $3,499~48 GB usable · uses ~7.6 GB · ~72 tok/s est.
- YesApple M4 Max (128GB) from $3,499~96 GB usable · uses ~7.6 GB · ~72 tok/s est.
- YesAMD Ryzen AI Halo (128GB) from $3,999~96 GB usable · uses ~7.6 GB · ~27 tok/s est.
- YesApple M5 Max (128GB) from $3,599~96 GB usable · uses ~7.6 GB · ~81 tok/s est.
- YesNvidia DGX Spark (128GB) from $3,999~112 GB usable · uses ~7.6 GB · ~29 tok/s est.
- YesApple M3 Ultra (256GB) from $3,999~192 GB usable · uses ~7.6 GB · ~108 tok/s est.
Too small for Nemotron Nano 9B v2
See the full Nemotron Nano 9B v2 memory breakdown, or compare it against other models.
Sources
-
ollama.com · 1 source
Memory at Q4_K_M (7.6 GB = 6.08 GB weights + KV cache + overhead), Catalog updated 2026-11-01. See methodology.