RTX PRO 6000D Price & Used Prices: Which Local LLMs Can It Run?
The RTX PRO 6000D is NVIDIA's 2025 84GB data center card for China, running a 176B MoE at 2-bit. No fans or video outputs: servers only.
eBay
RTX PRO 6000D price history
eBay
As an eBay Partner, VRAMGlass may be compensated if you buy through the eBay links on this page. The price you pay stays the same.
Full RTX PRO 6000D specifications
- Memory84 GB · GDDR7 ECC
- Bandwidth1,398 GB/s
- FP16 / BF16385.2 TFLOPS
- FP8 / INT8770.5 / 770.5 TOPS
- Bus width
- 448-bit
- Architecture
- Blackwell (GB202)
- Cores
- 19,968
- Tensor cores
- 624
- Ecosystem
- CUDA
- Interface
- PCIe 5.0 x16
- NVLink
- Not supported
- Power
- 600 W
- Power connector
- 16-pin 12V-2x6
- Slots
- 2
- Length
- 267 mm
- Type
- Data center
- Launch date
- Sep 1, 2025
What LLMs can a single RTX PRO 6000D run?
A single 6000D tops out at Qwen3.8 Flash Next at 2-bit, about 132 tokens/s, with room to spare for 70B-class at 4-bit. Up to 35B, use 8-bit.
| Model | Size | Runs? | Speed t/s | Max context |
|---|---|---|---|---|
 Gemma 4 26B A4B25.2B (3.8B active) | 10.5 GB | Runs | 157.5 | 256K |
 Qwen3.6 27B27.8B | 11.8 GB | Runs | 79 | 256K |
| Qwen3.8 27B27.8B | 9.8 GB | Runs | 92.7 | 256K |
 GLM 4.7 Flash30B (3B active) | 11.9 GB | Runs | 166.3 | 198K |
| Gemma 4 31B30.7B | 11.8 GB | Runs | 76.3 | 256K |
| Qwen3.6 35B A3B36B (3B active) | 12.3 GB | Runs | 174.4 | 256K |
| Model | Size | Runs? | Speed t/s | Max context |
|---|---|---|---|---|
| Gemma 4 26B A4B25.2B (3.8B active) | 16.9 GB | Runs | 137.9 | 256K |
| Qwen3.6 27B27.8B | 16.8 GB | Runs | 57.7 | 256K |
| Qwen3.8 27B27.8B | 16.5 GB | Runs | 58.7 | 256K |
| GLM 4.7 Flash30B (3B active) | 18.3 GB | Runs | 151.3 | 198K |
| Gemma 4 31B30.7B | 18.3 GB | Runs | 52.2 | 256K |
| Qwen3.6 35B A3B36B (3B active) | 22.1 GB | Runs | 153.9 | 256K |
| Model | Size | Runs? | Speed t/s | Max context |
|---|---|---|---|---|
| Gemma 4 26B A4B25.2B (3.8B active) | 26.9 GB | Runs | 115.5 | 256K |
| Qwen3.6 27B27.8B | 28.6 GB | Runs | 35.3 | 256K |
| Qwen3.8 27B27.8B | 29 GB | Runs | 34.8 | 256K |
| GLM 4.7 Flash30B (3B active) | 31.8 GB | Runs | 127.1 | 198K |
| Gemma 4 31B30.7B | 32.6 GB | Runs | 30.8 | 256K |
| Qwen3.6 35B A3B36B (3B active) | 36.9 GB | Runs | 130.7 | 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.
Full calculation rules are on the Methodology page.
What LLMs can multiple RTX PRO 6000D cards run?
Two 6000Ds (168GB) run DeepSeek V4 Flash at 4-bit at about 88 tokens/s; eight (672GB) run Kimi K2.6 at 4-bit. No NVLink.
| Model | Size | Cards | Total price | Total VRAM | Speed t/s | Total power |
|---|---|---|---|---|---|---|
| Qwen3.8 Flash Next176B (6B active) | 78.9 GB | 1 card | No price | 84 GB | 132 | 600 W |
 DeepSeek V4 Flash284B (13B active) | 96.8 GB | 2 cards | No price | 168 GB | 112.1 | 1,200 W |
 Hy3295B (21B active) | 107.2 GB | 2 cards | No price | 168 GB | 59.8 | 1,200 W |
| GLM 5.3 Flash320B (18B active) | 108.7 GB | 2 cards | No price | 168 GB | 94.6 | 1,200 W |
| GLM 5.3744B (40B active) | 253.9 GB | 4 cards | No price | 336 GB | 53.2 | 2,400 W |
| Hy4 preview770B (49B active) | 307.2 GBest. | 4 cards | No price | 336 GB | 41.2 | 2,400 W |
 Muse Spark Open816B (42B active) | 311.2 GB | 4 cards | No price | 336 GB | 48.1 | 2,400 W |
 Kimi K2.7 Code1,000B (32B active) | 339.5 GB | 8 cards | No price | 672 GB | 62.9 | 4,800 W |
| Kimi K2.61,000B (32B active) | 340.5 GB | 8 cards | No price | 672 GB | 62.8 | 4,800 W |
| DeepSeek V4 Pro1,600B (49B active) | 638.4 GBest. | 8 cards | No price | 672 GB | 43.4 | 4,800 W |
| Model | Size | Cards | Total price | Total VRAM | Speed t/s | Total power |
|---|---|---|---|---|---|---|
| Qwen3.8 Flash Next176B (6B active) | 111.3 GB | 2 cards | No price | 168 GB | 116.2 | 1,200 W |
| DeepSeek V4 Flash284B (13B active) | 155.1 GB | 2 cards | No price | 168 GB | 87.7 | 1,200 W |
| Hy3295B (21B active) | 182.2 GB | 4 cards | No price | 336 GB | 46.1 | 2,400 W |
| GLM 5.3 Flash320B (18B active) | 199.7 GB | 4 cards | No price | 336 GB | 65.1 | 2,400 W |
| GLM 5.3744B (40B active) | 467.3 GB | 8 cards | No price | 672 GB | 33.9 | 4,800 W |
| Hy4 preview770B (49B active) | 467.3 GB | 8 cards | No price | 672 GB | 29.6 | 4,800 W |
| Muse Spark Open816B (42B active) | 505.5 GB | 8 cards | No price | 672 GB | 33.2 | 4,800 W |
| DeepSeek V4.1 Flash763B (8 / 16B active) | 510.3 GB | 8 cards | No price | 672 GB | 57.2 | 4,800 W |
| Kimi K2.61,000B (32B active) | 583.7 GB | 8 cards | No price | 672 GB | 43.1 | 4,800 W |
| Kimi K2.7 Code1,000B (32B active) | 583.7 GB | 8 cards | No price | 672 GB | 43.1 | 4,800 W |
| Model | Size | Cards | Total price | Total VRAM | Speed t/s | Total power |
|---|---|---|---|---|---|---|
| DeepSeek V4 Flash284B (13B active) | 161.9 GB | 4 cards | No price | 336 GB | 85.5 | 2,400 W |
| Qwen3.8 Flash Next176B (6B active) | 188.2 GB | 4 cards | No price | 336 GB | 90.5 | 2,400 W |
| Hy3295B (21B active) | 317.7 GB | 8 cards | No price | 672 GB | 32.6 | 4,800 W |
| GLM 5.3 Flash320B (18B active) | 341 GB | 8 cards | No price | 672 GB | 43.9 | 4,800 W |
| Kimi K2.61,000B (32B active) | 594.5 GB | 8 cards | No price | 672 GB | 42.5 | 4,800 W |
| Kimi K2.7 Code1,000B (32B active) | 594.5 GB | 8 cards | No price | 672 GB | 42.5 | 4,800 W |
Rows marked “Engram in RAM” need about 203 GB of extra system RAM. Full calculation rules are on the Methodology page.
Who it suits
Good fit
- You can source the China-market version and want 84GB on one card
70B-class dense models at 4-bit fit with plenty to spare
- Running Qwen3.8 Flash Next at 2-bit
One card holds it, at about 132 tokens/s
- You already have GPU server racks
Like the RTX PRO 6000 Server Edition, it has no fan and relies on chassis airflow for cooling
Not a good fit
- Putting it in a tower or using it as a display card
It has no fan and can't output video
- You want the full PRO 6000's speed
It has about 22% less bandwidth and about 17% fewer cores
- Running large MoE models at 4-bit
Qwen3.8 Flash Next at 4-bit needs two cards
Before you buy
Servers only
The 6000D has no fan and looks just like the RTX PRO 6000 Server Edition, so it relies on strong server airflow for cooling. According to a teardown reported by MyDrivers, the card has 4 DP ports but can't output video, and under Windows it works only as a pure compute card. Power comes through one 16-pin connector.
Go by 1398 GB/s for bandwidth
Early media reports worked out 1568 GB/s from the memory clock, but HPE's official datasheet (part S6W21C) says 1398 GB/s, and we use the latter. If reviews or listings cite 1.57 TB/s, you can ignore it.
It looks the same as the PRO 6000 Server Edition
The two look almost identical, and teardowns show the same board layout; the 6000D simply has 4 fewer memory chips soldered on (28 instead of 32), which is why it has 84GB. Look for “6000D” and “84GB” in the listing, and check total VRAM in nvidia-smi when the card arrives.
Compared with similar GPUs
RTX PRO 6000D vs RTX PRO 6000, RTX PRO 5500, and GeForce RTX 4090D 48GB: price, VRAM, bandwidth, compute and local LLM speed compared.
| Spec | RTX PRO 6000D | RTX PRO 6000 | RTX PRO 5500 | GeForce RTX 4090D 48GB |
|---|---|---|---|---|
| Memory | 84 GB | 96 GB14% more | 84 GBSame | 48 GB43% less |
| Bandwidth | 1,398 GB/s | 1,792 GB/s28% higher | 1,398 GB/sSame | 1,008 GB/s28% lower |
| BF16 / FP16 compute | 385 TFLOPS | 500 TFLOPS30% higher | — | 294 TFLOPS24% lower |
| INT8 compute | 771 TOPS | 1,000 TOPS30% higher | — | 589 TOPS24% lower |
| Qwen3.8 27B speed (2-bit) | 92.7 t/s | 114.6 t/s24% faster | 92.7 t/sSame | 69.3 t/s25% slower |
| Largest dense model (4-bit) | 143B | 165B15% more | 143BSame | 79B45% less |
| Power | 600 W | 600 WSame | 600 WSame | 425 W29% lower |
| Interface | PCIe 5.0 x16 | PCIe 5.0 x16 | PCIe 5.0 x16 | PCIe 4.0 x16 |
| Released | 2025-09 | 2025-03 | 2026-09 | 2023-12 |
| eBay median |
As an eBay Partner, VRAMGlass may be compensated if you buy through the eBay links on this page. The price you pay stays the same.
RTX PRO 6000D rental price per hour
On Vast.ai, the RTX PRO 6000D rents for $1.26 per hour on demand, about $307/month at 8 hours a day. Buying one (Xianyu median $9,864) pays off in about 5.9 years, 2.9 years or 1 year 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 | $1.26/hr | $153/mo | $307/mo | $920/mo | Rent |
 XianyuUpdated 2 hr. ago | $9,864 | Payback ~5.9 yrsPower $13/mo | Payback ~2.9 yrsPower $26/mo | Payback ~1 yrPower $79/mo | Buy |
Break-even uses the US residential average ($0.18/kWh) and 600 W rated power, excluding resale value and the rest of the build.
Rental links are referral links: we may receive a commission or credit if you sign up through them.
Amazon.jp