RTX 6000 Ada Price & Used Prices: Which Local LLMs Can It Run?
Price alert
We'll email you when the eBay (US) price reaches your target.
The RTX 6000 Ada has 48GB of GDDR6 ECC memory with 960 GB/s of bandwidth. The median asking price is about $7,400 on eBay. At 4-bit quantization and 8K context it fits a dense model of up to about 79B parameters, at roughly 14 tokens/s.
eBay
RTX 6000 Ada price history
eBay
Buy links may carry affiliate tags; they do not change the price you pay.
Full RTX 6000 Ada specifications
- Memory48 GB · GDDR6 ECC
- Bandwidth960 GB/s
- FP16 / BF16364.3 TFLOPS
- FP8 / INT8728.5 / 728.5 TOPS
- Bus width
- 384-bit
- Architecture
- Ada Lovelace (AD102)
- Cores
- 18,176
- Tensor cores
- 568
- Ecosystem
- CUDA
- Interface
- PCIe 4.0 x16
- NVLink
- Not supported
- Power
- 300 W
- Power connector
- 16-pin 12VHPWR
- Slots
- 2
- Length
- 267 mm
- Type
- Workstation
- Launch date
- Sep 20, 2022
What LLMs can the RTX 6000 Ada run?
Models up to 50B parameters on a single RTX 6000 Ada, versions released since 2026 only
| Model | Size | Runs? | Speed t/s | Max context |
|---|---|---|---|---|
 Gemma 4 E4B8B | 3.8 GB | Runs | 158.9 | 128K |
 Qwen3.5 9B9.7B | 4.1 GB | Runs | 147.1 | 256K |
| Gemma 4 12B12B | 4.7 GB | Runs | 128.4 | 256K |
| Gemma 4 26B A4B25.2B (3.8B active) | 10.5 GB | Runs | 153.7 | 256K |
| Qwen3.6 27B27.8B | 11.8 GB | Runs | 55.9 | 256K |
| Qwen3.8 27B27.8B | 9.8 GB | Runs | 66.4 | 256K |
 GLM 4.7 Flash30B (3B active) | 11.9 GB | Runs | 166.8 | 198K |
| Gemma 4 31B30.7B | 11.8 GB | Runs | 53.9 | 256K |
| Qwen3.6 35B A3B36B (3B active) | 12.3 GB | Runs | 179.5 | 256K |
| Model | Size | Runs? | Speed t/s | Max context |
|---|---|---|---|---|
| Gemma 4 E4B8B | 5 GB | Runs | 125.1 | 128K |
| Qwen3.5 9B9.7B | 5.7 GB | Runs | 110.3 | 256K |
| Gemma 4 12B12B | 7.1 GB | Runs | 89.4 | 256K |
| Gemma 4 26B A4B25.2B (3.8B active) | 16.9 GB | Runs | 127 | 256K |
| Qwen3.6 27B27.8B | 16.8 GB | Runs | 40 | 256K |
| Qwen3.8 27B27.8B | 16.5 GB | Runs | 40.7 | 256K |
| GLM 4.7 Flash30B (3B active) | 18.3 GB | Runs | 144.9 | 198K |
| Gemma 4 31B30.7B | 18.3 GB | Runs | 36 | 256K |
| Qwen3.6 35B A3B36B (3B active) | 22.1 GB | Runs | 148.6 | 256K |
| Model | Size | Runs? | Speed t/s | Max context |
|---|---|---|---|---|
| Gemma 4 E4B8B | 8.2 GB | Runs | 79.8 | 128K |
| Qwen3.5 9B9.7B | 9.5 GB | Runs | 69.2 | 256K |
| Gemma 4 12B12B | 12.7 GB | Runs | 52.3 | 256K |
| Gemma 4 26B A4B25.2B (3.8B active) | 26.9 GB | Runs | 99.9 | 256K |
| Qwen3.6 27B27.8B | 28.6 GB | Runs | 24 | 256K |
| Qwen3.8 27B27.8B | 29 GB | Runs | 23.7 | 256K |
| GLM 4.7 Flash30B (3B active) | 31.8 GB | Runs | 113.5 | 198K |
| Gemma 4 31B30.7B | 32.6 GB | Runs | 20.8 | 202K |
| Qwen3.6 35B A3B36B (3B active) | 36.9 GB | Runs | 117.9 | 256K |
RunsFits fully in VRAM; speed is estimated from VRAM bandwidth.
Needs RAM offloadMoE only: expert weights sit in system RAM, so speed is estimated from 70 GB/s RAM bandwidth.
Too bigWon’t fit on one card at this quantization, even with RAM offload.
Dual, 4x and 8x RTX 6000 Ada for LLMs: which models fit?
Cards needed for 50B+ models released since 2026, with vLLM tensor parallelism at 32K context
| Model | Size | Cards | Total price | Total VRAM | Speed t/s | Total power |
|---|---|---|---|---|---|---|
| Qwen3.8 Flash Next176B (6B active) | 78.9 GB | 2 cards | $14,800 | 96 GB | 119.5 | 600 W |
 DeepSeek V4 Flash284B (13B active) | 96.8 GB | 4 cards | $29,600 | 192 GB | 96.1 | 1,200 W |
 Hy3295B (21B active) | 107.2 GB | 4 cards | $29,600 | 192 GB | 44.9 | 1,200 W |
| GLM 5.3 Flash320B (18B active) | 108.7 GB | 4 cards | $29,600 | 192 GB | 77.4 | 1,200 W |
| GLM 5.3744B (40B active) | 253.9 GB | 8 cards | $59,200 | 384 GB | 39.4 | 2,400 W |
| Hy4 preview770B (49B active) | 286.1 GBest. | 8 cards | $59,200 | 384 GB | 29.6 | 2,400 W |
 Kimi K2.7 Code1,000B (32B active) | 339.5 GB | 8 cards | $59,200 | 384 GB | 47.6 | 2,400 W |
| Model | Size | Cards | Total price | Total VRAM | Speed t/s | Total power |
|---|---|---|---|---|---|---|
| Qwen3.8 Flash Next176B (6B active) | 111.3 GB | 4 cards | $29,600 | 192 GB | 100.6 | 1,200 W |
| DeepSeek V4 Flash284B (13B active) | 155.1 GB | 4 cards | $29,600 | 192 GB | 70.5 | 1,200 W |
| Hy3295B (21B active) | 182.2 GB | 8 cards | $59,200 | 384 GB | 33.5 | 2,400 W |
| GLM 5.3 Flash320B (18B active) | 199.7 GB | 8 cards | $59,200 | 384 GB | 49.6 | 2,400 W |
| Model | Size | Cards | Total price | Total VRAM | Speed t/s | Total power |
|---|---|---|---|---|---|---|
| DeepSeek V4 Flash284B (13B active) | 161.9 GB | 4 cards | $29,600 | 192 GB | 68.4 | 1,200 W |
| Qwen3.8 Flash Next176B (6B active) | 188.2 GB | 8 cards | $59,200 | 384 GB | 73.3 | 2,400 W |
| Hy3295B (21B active) | 317.7 GB | 8 cards | $59,200 | 384 GB | 23 | 2,400 W |
| GLM 5.3 Flash320B (18B active) | 341 GB | 8 cards | $59,200 | 384 GB | 31.8 | 2,400 W |
Card counts are 1 / 2 / 4 / 8, each using 90% of its VRAM. Speed is based on one card’s bandwidth; price covers GPUs only. No NVLink; cards talk over PCIe. Whether it runs also depends on vLLM support.
RTX 6000 Ada rental price per hour
On-demand rental of the RTX 6000 Ada starts at $0.7 per hour (Vast.ai), about $169/month at 8 hours a day. Buying one (eBay median $7,400) pays off in about 7.9 years, 4 years or 1.3 years at 4, 8 or 24 hours a day.
| Option | Price | 4 h/day | 8 h/day | 24 h/day | View |
|---|---|---|---|---|---|
 Vast.aiRentUpdated 47 min. ago | $0.7/hr | $85/mo | $169/mo | $508/mo | Rent |
 RunPodRentUpdated 47 min. ago | $0.74/hr | $90/mo | $180/mo | $540/mo | Rent |
 eBayUpdated 2 hr. ago | $7,400 | Payback ~7.9 yrsPower $7/mo | Payback ~4 yrsPower $13/mo | Payback ~1.3 yrsPower $39/mo | Buy |
Break-even uses the US residential average ($0.18/kWh) and 300 W rated power, excluding resale value and the rest of the build.
Other markets
Amazon.jp
XianyuBuy links may carry affiliate tags; they do not change the price you pay.
FAQ
How large a model can the RTX 6000 Ada run?
A single RTX 6000 Ada has 48GB of GDDR6 ECC VRAM. At 4-bit quantization and 8K context it fits a dense model of up to about 79B parameters, or about 43B at 8-bit.
Can the RTX 6000 Ada run a 70B model?
Yes. At 4-bit with an 8K context a 70B dense model needs about 43GB, which fits in the RTX 6000 Ada's 48GB.
What are the best LLMs to run on the RTX 6000 Ada?
Among models released in 2026, the largest dense model that fits entirely in VRAM at 4-bit is Gemma 4 31B, at an estimated 36 tokens/s. Among MoE models, Qwen3.6 35B A3B is the fastest at about 148.6 tokens/s. The full list is in the table above.
How many tokens per second does the RTX 6000 Ada get on LLMs?
Estimated from memory bandwidth at 4-bit and 8K context: 8B dense: about 120.1 tokens/s, 14B dense: about 72.9 tokens/s, 32B dense: about 34 tokens/s, and 70B dense: about 16.1 tokens/s. MoE models read only the active parameters for each token, so they run much faster. Real-world results are usually 70%–100% of the estimate.
What LLMs can dual RTX 6000 Ada cards run?
With vLLM tensor parallelism at 4-bit and 32K context, two RTX 6000 Ada cards cannot fit any model of 50B or larger released in 2026. At 4-bit with 32K context the minimum is 4 cards, which fits Qwen3.8 Flash Next and DeepSeek V4 Flash.
How much does a RTX 6000 Ada cost?
As of Sep 29, 2026: eBay median $7,400 (11 listings) and Xianyu median $9,745 (11 listings). Figures are medians of live listings, refreshed every 6 hours.
Is the RTX 6000 Ada price going up or down?
As of Sep 29, 2026, the eBay median is up 5.7% over 7 days, up 5.7% over 30 days.
How much does it cost to rent a RTX 6000 Ada per hour?
As of Sep 29, 2026: Vast.ai at $0.7 per hour and RunPod at $0.74 per hour. All are single-GPU on-demand rates, excluding storage and data transfer.
Is it cheaper to buy or rent a RTX 6000 Ada at 8 hours a day?
Taking the eBay median of $7,400 and electricity at $0.18 per kWh, at 8 hours a day buying pays for itself in about 4 years (versus Vast.ai at $0.7 per hour). If you will use it for longer than 4 years, buy; otherwise, rent.
RTX 6000 Ada vs Radeon PRO W7900: which is better for LLMs?
The Radeon PRO W7900 has 48GB of VRAM and 864 GB/s of bandwidth; the RTX 6000 Ada has 48GB and 960 GB/s. At the eBay median, the Radeon PRO W7900 costs about $3,550, 52% less than the RTX 6000 Ada ($7,400). For 70B dense models at 4-bit, the RTX 6000 Ada is estimated at about 16.1 tokens/s and the Radeon PRO W7900 at about 10.4 tokens/s.