24h drops
- Radeon RX 7900 XTX$1,250-3.8%
DGX Spark 128GB$8,081-3.8%- MacBook Pro M4 Max 128GB$5,149-2.4%
- GeForce RTX 3060 12GB$400-1.2%
- Mac Studio M5 Ultra 96GB$7,274-1.0%
24h rises
- CMP 170HX 40GB$2,934+19.8%
- GeForce RTX 4060 Ti 16GB$750+4.9%
Arc Pro B70$1,850+2.8%- Radeon RX 9070 XT$1,023+2.3%
- GeForce RTX 5090$8,297+2.2%
Most listings
- GeForce RTX 5090$8,297128 listings
- GeForce RTX 3090$1,799108 listings
- GeForce RTX 5080$2,074102 listings
- GeForce RTX 3060 12GB$40098 listings
- GeForce RTX 5070$89991 listings
Latest release
DeepSeek V4.1 Flash763BQ4444.7 GB
Muse Spark Open816BQ4505.5 GB
Hy4 preview770BQ4467.3 GB
GLM 5.3744BQ4467.3 GB- GLM 5.3 Flash320BQ4199.7 GB
Local LLM GPU Ranking
eBay
| Model | 30d trend | Ecosystem | |||||||
|---|---|---|---|---|---|---|---|---|---|
| H100 PCIe | No price in this market | — | 80 | 2,000 | 756 | 1,513 | 350 | CUDA | |
| RTX PRO 6000 | $22,35012 listings | -0.7% | 96 | 1,792 | 500 | 1,000 | 600 | CUDA | |
| GeForce RTX 5090 | $8,297128 listings | +2.2% | 32 | 1,792 | 419 | 838 | 575 | CUDA | |
| RTX PRO 6000D | No price in this market | — | 84 | 1,398 | 385.2 | 770.5 | 600 | CUDA | |
| L40S | $8,97418 listings | 0.0% | 48 | 864 | 362.1 | 733 | 350 | CUDA | |
| RTX 6000 Ada | $7,9414 listings | 0.0% | 48 | 960 | 364.3 | 728.5 | 300 | CUDA | |
| GeForce RTX 4090 | $3,75870 listings | +0.2% | 24 | 1,008 | 330.3 | 660.6 | 450 | CUDA | |
| GeForce RTX 4090 48GB | No price in this market | — | 48 | 1,008 | 330.3 | 660.6 | 450 | CUDA | |
| A100 40GB PCIe | $7,75015 listings | 0.0% | 40 | 1,555 | 312 | 624 | 250 | CUDA | |
| A100 80GB PCIe | $18,99912 listings | 0.0% | 80 | 1,935 | 312 | 624 | 300 | CUDA | |
| GeForce RTX 5090 D | No price in this market | — | 32 | 1,792 | 296.9 | 593.8 | 575 | CUDA | |
| GeForce RTX 5090 D V2 | No price in this market | — | 24 | 1,344 | 296.9 | 593.8 | 575 | CUDA | |
| GeForce RTX 4090D 48GB | No price in this market | — | 48 | 1,008 | 294.3 | 588.5 | 425 | CUDA | |
| RTX PRO 5000 48GB | $7,90015 listings | +2.0% | 48 | 1,344 | 258 | 516 | 300 | CUDA | |
| RTX PRO 5000 72GB | $10,7223 listings | 0.0% | 72 | 1,344 | 258 | 516 | 300 | CUDA | |
| GeForce RTX 5080 | $2,074102 listings | +1.2% | 16 | 960 | 225.1 | 450.2 | 360 | CUDA | |
| RTX PRO 4500 | $5,00013 listings | 0.0% | 32 | 896 | 210.9 | 421.8 | 200 | CUDA | |
| GeForce RTX 4080 SUPER 32GB | No price in this market | — | 32 | 736 | 208.9 | 417.8 | 320 | CUDA | |
| CMP 170HX 40GB | $2,9343 listings | +19.8% | 40 | 1,560 | 202 | 404 | 250 | CUDA | |
| CMP 170HX 64GB | $3,0007 listings | 0.0% | 64 | 1,493 | 202 | 404 | 250 | CUDA | |
| GeForce RTX 4080 | $1,39951 listings | 0.0% | 16 | 717 | 195 | 389.9 | 320 | CUDA | |
| Radeon RX 9070 XT | $1,02376 listings | +2.3% | 16 | 640 | 195 | 389 | 304 | ROCm | |
| Radeon AI PRO R9700 | $2,0905 listings | 0.0% | 32 | 640 | 191 | 383 | 300 | ROCm | |
| Arc Pro B70 | $1,85017 listings | +2.8% | 32 | 608 | 183.5 | 367 | 230 | oneAPI | |
| GeForce RTX 5070 Ti | $1,36570 listings | +1.1% | 16 | 896 | 175.8 | 351.5 | 300 | CUDA | |
| RTX PRO 4000 | $2,9888 listings | 0.0% | 24 | 672 | 161.3 | 322.5 | 145 | CUDA | |
| RTX A6000 | $4,89916 listings | -1.0% | 48 | 768 | 154.9 | 309.7 | 300 | CUDA | |
| GeForce RTX 3090 | $1,799108 listings | 0.0% | 24 | 936 | 142.3 | 284.7 | 350 | CUDA | |
| DGX Spark 128GB | $8,08123 listings | -3.8% | 128 | 273 | 125 | 250 | 240 | CUDA | |
| GeForce RTX 5070 | $89991 listings | 0.0% | 12 | 672 | 123.5 | 247 | 250 | CUDA | |
| GeForce RTX 2080 Ti 22GB | $5513 listings | — | 22 | 616 | 107.6 | 215.2 | 250 | CUDA | |
| Arc Pro B60 | $9368 listings | 0.0% | 24 | 456 | 98.5 | 197 | 200 | oneAPI | |
| Arc Pro B65 | No price in this market | — | 32 | 608 | 98.5 | 197 | 200 | oneAPI | |
| GeForce RTX 5060 Ti 16GB | $85458 listings | +0.5% | 16 | 448 | 94.9 | 189.8 | 180 | CUDA | |
| Instinct MI210 | $4,99411 listings | 0.0% | 64 | 1,638 | 181 | 181 | 300 | ROCm | |
| GeForce RTX 4060 Ti 16GB | $7509 listings | +4.9% | 16 | 288 | 88.3 | 176.5 | 165 | CUDA | |
| Tesla T10 | $4955 listings | 0.0% | 16 | 403 | 80 | 160 | 150 | CUDA | |
| Radeon PRO W7900 | $3,5993 listings | 0.0% | 48 | 864 | 123 | 123 | 295 | ROCm | |
| Radeon RX 7900 XTX | $1,25029 listings | -3.8% | 24 | 960 | 123 | 123 | 355 | ROCm | |
| Radeon RX 7900 XT | $81029 listings | +1.3% | 20 | 800 | 103 | 103 | 315 | ROCm | |
| GeForce RTX 3060 12GB | $40098 listings | -1.2% | 12 | 360 | 51 | 101.9 | 170 | CUDA | |
| Radeon RX 6950 XT | $69216 listings | +0.3% | 16 | 576 | 47.3 | 94.6 | 335 | ROCm | |
| Instinct MI100 | $1,5037 listings | 0.0% | 32 | 1,229 | 92.3 | 92.3 | 300 | ROCm | |
| Radeon PRO W7800 | $2,49211 listings | 0.0% | 32 | 576 | 90.4 | 90.4 | 260 | ROCm | |
| Radeon RX 7800 XT | $60032 listings | 0.0% | 16 | 624 | 74.7 | 74.7 | 263 | ROCm | |
| Ryzen AI Max+ 395 128GB | $4,46420 listings | +1.8% | 128 | 256 | 59.4 | 59.4 | 120 | ROCm | |
| Tesla V100 16GB | $37024 listings | 0.0% | 16 | 900 | 112 | 56.1 | 250 | CUDA | |
| Tesla V100 32GB | $89518 listings | 0.0% | 32 | 900 | 112 | 56.1 | 250 | CUDA | |
| Instinct MI50 32GB | $7344 listings | 0.0% | 32 | 1,024 | 26.5 | 53 | 300 | ROCm | |
| Tesla P40 | $38425 listings | -0.8% | 24 | 347 | — | 47 | 250 | CUDA | |
| Mac Studio M3 Ultra 512GB | $22,90013 listings | +0.2% | 512 | 819 | — | — | 480 | Metal | |
| Mac Studio M4 Max 128GB | $5,8005 listings | 0.0% | 128 | 546 | — | — | 480 | Metal | |
| Mac Studio M5 Max 128GB | No price in this market | — | 128 | 614 | — | — | 480 | Metal | |
| Mac Studio M5 Ultra 96GB | $7,27412 listings | -1.0% | 96 | 1,229 | — | — | 480 | Metal | |
| MacBook Pro M4 Max 128GB | $5,14912 listings | -2.4% | 128 | 546 | — | — | 140 | Metal | |
| MacBook Pro M5 Max 128GB | $7,54920 listings | +2.0% | 128 | 614 | — | — | 140 | Metal | |
| RTX PRO 5500 | No price in this market | — | 84 | 1,398 | — | — | 600 | CUDA |
No GPUs match “”.
Log in to add GPUs to your watchlist and see it on any device. Log in
No GPUs in your watchlist yet. Click the ☆ before a model name to add one.
| Spec | Price per stick | Price per GB | Max channels | Max bandwidth | Max memory |
|---|---|---|---|---|---|
| 16 GB | $225137 listings | $14.1 | 2 | 96 GB/s | 64 GB4 sticks × 16 GB |
| 32 GB | $48883 listings | $15.3 | 2 | 96 GB/s | 128 GB4 sticks × 32 GB |
| 32 GB | $1,25031 listings | $39.1 | 24 | 1,075.2 GB/s | 768 GB24 sticks × 32 GB |
| 64 GB | $2,60016 listings | $40.6 | 24 | 1,075.2 GB/s | 1,536 GB24 sticks × 64 GB |
Choose hardware for local LLM deployment
Find the right GPU for local LLMs. Compare VRAM, GPU prices and model memory requirements to choose hardware that fits your models and budget.
What is VRAM, and how much do you need?
VRAM is the fast memory on a graphics card. Local LLM inference needs space for model weights, the context (KV) cache and runtime buffers. Quantization can reduce weight memory, while longer prompts and more simultaneous users need additional memory. A model fitting in VRAM does not guarantee a particular speed.
Plan a local deployment
Choose a model and quantization, set the context length, and check both GPU memory and system RAM. CPU or expert offloading can make a large model fit with less VRAM, but it depends on RAM bandwidth and can be much slower. Check CUDA, ROCm or Metal support before buying hardware.
Read the rankings and price data
Compare VRAM capacity first, then bandwidth, power and software support. Our prices are median asking prices, not completed sales; sample counts, observation dates and stale-price labels help you judge their usefulness. INT8 throughput alone is not an LLM benchmark.
