24h drops
GeForce RTX 3060 12GB$400-9.9%
Arc Pro B70$1,587-9.2%- Radeon RX 7900 XTX$1,150-4.2%
- Ryzen AI Max+ 395 128GB$3,650-3.9%
- GeForce RTX 5070$850-2.9%
24h rises
- RTX PRO 4000$3,245+8.2%
- Tesla V100 16GB$325+4.2%
- DGX Spark 128GB$7,207+3.0%
- RTX PRO 4500$5,245+2.9%
- GeForce RTX 5070 Ti$1,340+2.1%
Most listings
- GeForce RTX 5080$1,900138 listings
- GeForce RTX 5090$6,980121 listings
- GeForce RTX 3060 12GB$400117 listings
- GeForce RTX 3090$1,800108 listings
- GeForce RTX 5070$850100 listings
Latest release
DeepSeek V4.1 Flash763BQ4444.7 GB
Hy4 preview770BQ4467.3 GB
GLM 5.3744BQ4467.3 GB- GLM 5.3 Flash320BQ4199.7 GB
Qwen3.8 Flash Next176BQ4111.3 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 | $19,25012 listings | 0.0% | 96 | 1,792 | 500 | 1,000 | 600 | CUDA | |
| GeForce RTX 5090 | $6,980121 listings | -0.3% | 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 | $7,4009 listings | +0.3% | 48 | 960 | 364.3 | 728.5 | 300 | CUDA | |
| GeForce RTX 4090 | $3,50071 listings | 0.0% | 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 | $7,01514 listings | 0.0% | 40 | 1,555 | 312 | 624 | 250 | CUDA | |
| A100 80GB PCIe | $17,6378 listings | +1.4% | 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 | $8,54014 listings | -2.8% | 48 | 1,344 | 258 | 516 | 300 | CUDA | |
| RTX PRO 5000 72GB | No price in this market | — | 72 | 1,344 | 258 | 516 | 300 | CUDA | |
| GeForce RTX 5080 | $1,900138 listings | -1.6% | 16 | 960 | 225.1 | 450.2 | 360 | CUDA | |
| GeForce RTX 4080 SUPER 32GB | No price in this market | — | 32 | 736 | 208.9 | 417.8 | 320 | CUDA | |
| RTX PRO 4500 | $5,24510 listings | +2.9% | 32 | 896 | 202.1 | 404.3 | 200 | CUDA | |
| CMP 170HX 40GB | No price in this market | — | 40 | 1,560 | 202 | 404 | 250 | CUDA | |
| CMP 170HX 64GB | No price in this market | — | 64 | 1,493 | 202 | 404 | 250 | CUDA | |
| GeForce RTX 4080 | $1,40051 listings | 0.0% | 16 | 717 | 195 | 389.9 | 320 | CUDA | |
| Radeon RX 9070 XT | $97682 listings | -0.4% | 16 | 640 | 195 | 389 | 304 | ROCm | |
| Radeon AI PRO R9700 | $2,1997 listings | 0.0% | 32 | 640 | 191 | 383 | 300 | ROCm | |
| Arc Pro B70 | $1,5875 listings | -9.2% | 32 | 608 | 183.5 | 367 | 230 | oneAPI | |
| GeForce RTX 5070 Ti | $1,34093 listings | +2.1% | 16 | 896 | 175.8 | 351.5 | 300 | CUDA | |
| RTX PRO 4000 | $3,2458 listings | +8.2% | 24 | 672 | 161.3 | 322.5 | 145 | CUDA | |
| RTX A6000 | $5,09720 listings | +1.9% | 48 | 768 | 154.9 | 309.7 | 300 | CUDA | |
| GeForce RTX 3090 | $1,800108 listings | 0.0% | 24 | 936 | 142.3 | 284.7 | 350 | CUDA | |
| DGX Spark 128GB | $7,2075 listings | +3.0% | 128 | 273 | 125 | 250 | 240 | CUDA | |
| GeForce RTX 5070 | $850100 listings | -2.9% | 12 | 672 | 123.5 | 247 | 250 | CUDA | |
| GeForce RTX 2080 Ti 22GB | $5513 listings | 0.0% | 22 | 616 | 107.6 | 215.2 | 250 | CUDA | |
| Arc Pro B60 | $79710 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 | $80063 listings | 0.0% | 16 | 448 | 94.9 | 189.8 | 180 | CUDA | |
| Instinct MI210 | $5,04412 listings | 0.0% | 64 | 1,638 | 181 | 181 | 300 | ROCm | |
| GeForce RTX 4060 Ti 16GB | $7005 listings | 0.0% | 16 | 288 | 88.3 | 176.5 | 165 | CUDA | |
| Tesla T10 | $4955 listings | — | 16 | 403 | 80 | 160 | 150 | CUDA | |
| Radeon PRO W7900 | $3,5503 listings | 0.0% | 48 | 864 | 123 | 123 | 295 | ROCm | |
| Radeon RX 7900 XTX | $1,15029 listings | -4.2% | 24 | 960 | 123 | 123 | 355 | ROCm | |
| Radeon RX 7900 XT | $80030 listings | 0.0% | 20 | 800 | 103 | 103 | 315 | ROCm | |
| GeForce RTX 3060 12GB | $400117 listings | -9.9% | 12 | 360 | 51 | 101.9 | 170 | CUDA | |
| Radeon RX 6950 XT | $65015 listings | 0.0% | 16 | 576 | 47.3 | 94.6 | 335 | ROCm | |
| Instinct MI100 | $8806 listings | 0.0% | 32 | 1,229 | 92.3 | 92.3 | 300 | ROCm | |
| Radeon PRO W7800 | $2,34612 listings | 0.0% | 32 | 576 | 90.4 | 90.4 | 260 | ROCm | |
| Radeon RX 7800 XT | $60041 listings | 0.0% | 16 | 624 | 74.7 | 74.7 | 263 | ROCm | |
| Ryzen AI Max+ 395 128GB | $3,65019 listings | -3.9% | 128 | 256 | 59.4 | 59.4 | 120 | ROCm | |
| Tesla V100 16GB | $32535 listings | +4.2% | 16 | 900 | 112 | 56.1 | 250 | CUDA | |
| Tesla V100 32GB | $89520 listings | -0.4% | 32 | 900 | 112 | 56.1 | 250 | CUDA | |
| Instinct MI50 32GB | $7686 listings | 0.0% | 32 | 1,024 | 26.5 | 53 | 300 | ROCm | |
| Tesla P40 | $39716 listings | -0.5% | 24 | 347 | — | 47 | 250 | CUDA | |
| Mac Studio M3 Ultra 512GB | $22,95014 listings | 0.0% | 512 | 819 | — | — | 480 | Metal | |
| Mac Studio M4 Max 128GB | $5,9998 listings | 0.0% | 128 | 546 | — | — | 480 | Metal | |
| Mac Studio M5 Max 128GB | No price in this market | — | 128 | 614 | — | — | — | Metal | |
| MacBook Pro M4 Max 128GB | $5,30013 listings | 0.0% | 128 | 546 | — | — | 140 | Metal | |
| MacBook Pro M5 Max 128GB | $7,19921 listings | 0.0% | 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.
DDR4 RAM prices
eBay
| Spec | Price per stick | Price per GB | Max channels | Max bandwidth | Max memory |
|---|---|---|---|---|---|
| 16 GB | $90189 listings | $5.6 | 2 | 51.2 GB/s | 64 GB4 sticks × 16 GB |
| 32 GB | $22584 listings | $7 | 2 | 51.2 GB/s | 128 GB4 sticks × 32 GB |
| 16 GB | $11850 listings | $7.4 | 8 | 170.6 GB/s | 128 GB8 sticks × 16 GB |
| 32 GB | $21443 listings | $6.7 | 8 | 170.6 GB/s | 256 GB8 sticks × 32 GB |
DDR5 RAM prices
eBay
| Spec | Price per stick | Price per GB | Max channels | Max bandwidth | Max memory |
|---|---|---|---|---|---|
| 16 GB | $225116 listings | $14.1 | 2 | 96 GB/s | 64 GB4 sticks × 16 GB |
| 32 GB | $45070 listings | $14.1 | 2 | 96 GB/s | 128 GB4 sticks × 32 GB |
| 32 GB | $1,23420 listings | $38.6 | 12 | 537.6 GB/s | 384 GB12 sticks × 32 GB |
| 64 GB | $2,69910 listings | $42.2 | 12 | 537.6 GB/s | 768 GB12 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.
