RigPrice.

Best hardware for Gemma 4 12B

Light assistant for mid-range GPUs.

12B parameters · dense · gemma family

Our picks for this model

Cheapest

1× Intel Arc B580

$300 on eBay ↗ · ~29.8 tok/s est.

one card, no extra setup

Intel card: runs well with Vulkan builds, but expect more setup than an NVIDIA card.

Easiest

1× NVIDIA GeForce RTX 3060 12GB

$305 on eBay ↗ · ~23.5 tok/s est.

one card, no extra setup

Fastest

1× NVIDIA GeForce RTX 5090

$5,500 on eBay ↗ · ~117 tok/s est.

one card, no extra setup

Rule-based picks at Q4_K_M, from live screened prices (how we estimate speed and choose picks). Every option is ranked below.

Q4_K_M

Minimum VRAM: 10.05 GB (file 7.66 GB + context/runtime headroom at 8k ctx; see methodology).

Cheapest fitting cloud offer: Vast.ai $0.071/hr (rtx-a4000 class, on-demand) · cloud prices checked 2026-09-08.

ConfigScreened priceTotal VRAMEst. wattsEst. tokens/secBreakeven vs cloudVerdict
1× Intel Arc B580 our pick · Cheapest
Intel card: more setup than NVIDIA for local AI
$30012 GB265 W (well below this table's average)~29.887 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 3060 12GB our pick · Easiest$30512 GB245 W (well below this table's average)~23.5 (well below this table's average)67 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 5090 our pick · Fastest$5,50032 GB650 W~117 (well above this table's average)neverCloud always cheaper at this power price
1× Intel Arc A770 16GB
Intel card: more setup than NVIDIA for local AI
$32016 GB300 W (well below this table's average)~36.5104 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 3080 10GB
fits with a small context window (about 4k)
$37510 GB395 W~49.6292 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 3080 12GB$435
+ shipping unknown
12 GB425 W~59.61,064 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 5060 Ti 16GB$70616 GB255 W (well below this table's average)~29.2 (well below this table's average)209 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 4070 Ti SUPER$80016 GB360 W~43.9471 moRenting wins at 40 h/mo
1× AMD Radeon RX 7900 XTX
AMD card: more setup than NVIDIA for local AI
$94524 GB430 W~62.73,660 moRenting wins at 40 h/mo
1× NVIDIA RTX A4000$95016 GB215 W (well below this table's average)~29.2 (well below this table's average)206 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 4080$1,00016 GB395 W~46.8722 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 5070 Ti$1,10016 GB375 W~58.5589 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 4080 SUPER$1,19516 GB395 W~48.11,149 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 5080$1,49016 GB435 W~62.78,926 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 3090$1,50024 GB425 W~61.14,663 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 3090 Ti$1,61024 GB525 W~65.8neverCloud always cheaper at this power price
1× NVIDIA RTX A5000$2,20024 GB305 W~50.1653 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 4090$2,95024 GB525 W~65.8neverCloud always cheaper at this power price
2× NVIDIA GeForce RTX 3090$3,00048 GB775 W (well above this table's average)~61.1neverCloud always cheaper at this power price
1× NVIDIA RTX A6000$4,27048 GB375 W~50.12,295 moRenting wins at 40 h/mo
2× NVIDIA RTX A5000$4,69948 GB535 W~50.1neverCloud always cheaper at this power price
2× NVIDIA GeForce RTX 4090$5,95048 GB975 W (well above this table's average)~65.8neverCloud always cheaper at this power price
4× NVIDIA GeForce RTX 3090$6,05096 GB1475 W (well above this table's average)~61.1neverCloud always cheaper at this power price
2× NVIDIA RTX A6000$8,57096 GB675 W~50.1neverCloud always cheaper at this power price
1× NVIDIA Tesla P40
Passive datacenter card: needs a cooling mod and is far slower than modern cards
$30824 GB325 W~22.7 (well below this table's average)128 moRenting wins at 40 h/mo
2× NVIDIA Tesla P40
Passive datacenter card: needs a cooling mod and is far slower than modern cards
$61848 GB575 W~22.7 (well below this table's average)neverCloud always cheaper at this power price
1× NVIDIA TITAN RTX
Turing-era card: much slower than an RTX 3090 for similar money
$89924 GB355 W~43.9386 moRenting wins at 40 h/mo
4× NVIDIA Tesla P40
Passive datacenter card: needs a cooling mod and is far slower than modern cards
$1,25696 GB1075 W (well above this table's average)~22.7 (well below this table's average)neverCloud always cheaper at this power price

Fits, but not currently buyable as a set: 4× NVIDIA RTX A5000 (96 GB) needs 4 screened cards and the market has 2. We price a multi-card build from that many separate listings, so it stays unpriced until they exist.

  • Our pick rows sit on top, then clean configs by price; cards with a caveat (cooling mod needed, or poor value for AI) group last, whatever their price. Watts and tokens/sec turn green or red when they sit far from this table's average (roughly 40% either way).
  • Prices link straight to the screened eBay listing; hover for the seller summary. Seller details and the report option live on each card's own page.
  • 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 are estimates, not benchmarks: spec-sheet memory bandwidth at 50% utilization divided by the model bytes read per token (how and why). Real speeds vary with the runtime and context length.
  • Breakeven and verdict use default assumptions (40 h/mo, $0.16/kWh, 24-month horizon, resale at 65% of the going rate); adjust them in the calculator. Hardware links are screened, not guaranteed.

Run your own numbers for Gemma 4 12B (Q4_K_M) in the buy-vs-rent calculator →

Q8_0

Minimum VRAM: 15.31 GB (file 12.67 GB + context/runtime headroom at 8k ctx; see methodology).

Cheapest fitting cloud offer: Vast.ai $0.071/hr (rtx-a4000 class, on-demand) · cloud prices checked 2026-09-08.

ConfigScreened priceTotal VRAMEst. wattsEst. tokens/secBreakeven vs cloudVerdict
1× Intel Arc A770 16GB
Intel card: more setup than NVIDIA for local AI
$32016 GB300 W (well below this table's average)~22.1104 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 5060 Ti 16GB$70616 GB255 W (well below this table's average)~17.7 (well below this table's average)209 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 4070 Ti SUPER$80016 GB360 W~26.5471 moRenting wins at 40 h/mo
1× AMD Radeon RX 7900 XTX
AMD card: more setup than NVIDIA for local AI
$94524 GB430 W~37.93,660 moRenting wins at 40 h/mo
1× NVIDIA RTX A4000$95016 GB215 W (well below this table's average)~17.7 (well below this table's average)206 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 4080$1,00016 GB395 W~28.3722 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 5070 Ti$1,10016 GB375 W~35.4589 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 4080 SUPER$1,19516 GB395 W~29.11,149 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 5080$1,49016 GB435 W~37.98,926 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 3090$1,50024 GB425 W~36.94,663 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 3090 Ti$1,61024 GB525 W~39.8neverCloud always cheaper at this power price
1× NVIDIA RTX A5000$2,20024 GB305 W (well below this table's average)~30.3653 moRenting wins at 40 h/mo
1× NVIDIA GeForce RTX 4090$2,95024 GB525 W~39.8neverCloud always cheaper at this power price
2× NVIDIA GeForce RTX 3090$3,00048 GB775 W (well above this table's average)~36.9neverCloud always cheaper at this power price
1× NVIDIA RTX A6000$4,27048 GB375 W~30.32,295 moRenting wins at 40 h/mo
2× NVIDIA RTX A5000$4,69948 GB535 W~30.3neverCloud always cheaper at this power price
1× NVIDIA GeForce RTX 5090$5,50032 GB650 W~70.7 (well above this table's average)neverCloud always cheaper at this power price
2× NVIDIA GeForce RTX 4090$5,95048 GB975 W (well above this table's average)~39.8neverCloud always cheaper at this power price
4× NVIDIA GeForce RTX 3090$6,05096 GB1475 W (well above this table's average)~36.9neverCloud always cheaper at this power price
2× NVIDIA RTX A6000$8,57096 GB675 W~30.3neverCloud always cheaper at this power price
1× NVIDIA Tesla P40
Passive datacenter card: needs a cooling mod and is far slower than modern cards
$30824 GB325 W~13.7 (well below this table's average)128 moRenting wins at 40 h/mo
2× NVIDIA Tesla P40
Passive datacenter card: needs a cooling mod and is far slower than modern cards
$61848 GB575 W~13.7 (well below this table's average)neverCloud always cheaper at this power price
1× NVIDIA TITAN RTX
Turing-era card: much slower than an RTX 3090 for similar money
$89924 GB355 W~26.5386 moRenting wins at 40 h/mo
4× NVIDIA Tesla P40
Passive datacenter card: needs a cooling mod and is far slower than modern cards
$1,25696 GB1075 W (well above this table's average)~13.7 (well below this table's average)neverCloud always cheaper at this power price

Fits, but not currently buyable as a set: 4× NVIDIA RTX A5000 (96 GB) needs 4 screened cards and the market has 2. We price a multi-card build from that many separate listings, so it stays unpriced until they exist.

  • Our pick rows sit on top, then clean configs by price; cards with a caveat (cooling mod needed, or poor value for AI) group last, whatever their price. Watts and tokens/sec turn green or red when they sit far from this table's average (roughly 40% either way).
  • Prices link straight to the screened eBay listing; hover for the seller summary. Seller details and the report option live on each card's own page.
  • 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 are estimates, not benchmarks: spec-sheet memory bandwidth at 50% utilization divided by the model bytes read per token (how and why). Real speeds vary with the runtime and context length.
  • Breakeven and verdict use default assumptions (40 h/mo, $0.16/kWh, 24-month horizon, resale at 65% of the going rate); adjust them in the calculator. Hardware links are screened, not guaranteed.

Run your own numbers for Gemma 4 12B (Q8_0) in the buy-vs-rent calculator →