Best hardware for Nemotron 3 Super 120B-A12B
121B parameters · nemotron family MoE : per-quant VRAM needs, the used-GPU configs that fit, and how buying compares with renting cloud GPUs. Hardware costs sum the cheapest listings that passed our trust screen, one per card the config needs (screened, not guaranteed). Eligible purchases are covered by the eBay Money Back Guarantee if an item never arrives or doesn't match its description.
Q4_K_M
Minimum VRAM: 93.33 GB (file 86.98 GB + context/runtime headroom at 8k ctx; see methodology).
No tracked cloud offer fits this quant's VRAM needs, so there is no breakeven to compute; any fitting hardware is shown buy-only.
| Config | Total VRAM | Cheapest screened hw cost | Est. watts | Tokens/sec | Breakeven vs cloud | Verdict |
|---|---|---|---|---|---|---|
| 4× NVIDIA Tesla P40
passive card, needs an added fan/shroud
| 96 GB | $1,099 4 screened listings: $259 + $270 + $280 + $290 + shipping unknown on 2 of 4 listings
report
25,244 feedback (99.9%) · returns accepted · listed 21 days | 1075 W | – | – | Buy-only; no cloud offer fits |
| 4× NVIDIA GeForce RTX 3090 | 96 GB | $4,974 4 screened listings: $1,240 + $1,240 + $1,245 + $1,249
report
39,860 feedback (99.7%) · returns accepted · listed 14 days | 1475 W | – | – | Buy-only; no cloud offer fits |
| 2× NVIDIA RTX A6000 | 96 GB | $7,948 2 screened listings: $3,949 + $3,999
report
23,219 feedback (99.9%) · Top Rated seller · returns accepted · listed 21 days | 675 W | – | – | Buy-only; no cloud offer fits |
Fits, but not currently buyable as a set: 4× NVIDIA RTX A5000 (96 GB) needs 4 screened cards and the market has 1. We price a multi-card build from that many separate listings, so it stays unpriced until they exist.
- Configs without a screened purchase option are hidden until listings clear the trust screen (a multi-day survival window on eBay).
- Multi-card costs are the sum of that many separate screened listings; the cheapest listing counted twice is not a price anyone can pay. Prices exclude the PSU, board and case a multi-card build usually also needs.
- Tokens/sec: benchmarks coming; every number will be source-linked. We never publish unattributed performance figures.
- Breakeven and verdict use default assumptions (40 h/mo, $0.16/kWh, 24-month horizon, resale at 65% of median ask); adjust them in the calculator. Hardware links are screened, not guaranteed.
Run your own numbers for Nemotron 3 Super 120B-A12B (Q4_K_M) in the buy-vs-rent calculator →
Q8_0
Minimum VRAM: 136.9 GB (file 128.47 GB + context/runtime headroom at 8k ctx; see methodology).
No tracked cloud offer fits this quant's VRAM needs, so there is no breakeven to compute; any fitting hardware is shown buy-only.
No screened hardware configs currently fit this quant.
- Configs without a screened purchase option are hidden until listings clear the trust screen (a multi-day survival window on eBay).
- Multi-card costs are the sum of that many separate screened listings; the cheapest listing counted twice is not a price anyone can pay. Prices exclude the PSU, board and case a multi-card build usually also needs.
- Tokens/sec: benchmarks coming; every number will be source-linked. We never publish unattributed performance figures.
- Breakeven and verdict use default assumptions (40 h/mo, $0.16/kWh, 24-month horizon, resale at 65% of median ask); adjust them in the calculator. Hardware links are screened, not guaranteed.
Run your own numbers for Nemotron 3 Super 120B-A12B (Q8_0) in the buy-vs-rent calculator →