NVIDIA · Hopper · 141 GB · Qwen3.8 27B · Q4_K_M at 8K context: ~180 tok/s
NVIDIA H200 NVL 141GB
The PCIe H200: 141 GB of HBM3e at 4.8 TB/s, enough for a 70B model at FP16 or a 400B at Q4 on one card. Data-center money, listed because it does appear on eBay.
Lowest price right now
$62,999
eBay · free shipping · $446 per GB · observed 2026-11-14 18:37 UTC
Buy the cheapest on eBay, $62,999
free shipping · Open box · t-traderz 19,971 · 99.9%
Price alert
One email per move, item plus shipping. Clear the price to hear about any drop. Manage alerts.
Price history
Daily low across every tracked vendor, last 6 days.
Where to buy
| Vendor | Price | Condition | Observed | |
|---|---|---|---|---|
| eBay cheapest active listing |
$62,999 free shipping |
new and used | 2026-11-14 18:37 UTC | Go to eBay |
On eBay now
11 listings passed our filters at the last check, 7 min ago. We check every 28 minutes. Cheapest delivered first. Seller reputation is feedback count and positive rate.
-
$62,999free shipping -
$64,020$64,000 + $20 shipping -
$65,000free shipping -
$76,999free shipping -
$87,456.19free shipping -
$92,000free shipping
What it runs
For each model, grouped by vendor with the newest first: the largest quant that fits with 8K of context and the estimated speed for one user, at 8K and at 32K of context. On a card, a model too big for its memory can still run with part of the weights in system RAM; we assume 64 GB, and the speed shown accounts for it. The model you picked on the ladder is highlighted. Estimates from the spec sheet, not measurements: see how we estimate.
| Model | Quant | Needs at 8K | Fit | Max context | Decode at 8K | At 32K | Prefill tok/s |
|---|---|---|---|---|---|---|---|
| DeepSeek | |||||||
| DeepSeek V4.1 Flash 552B-A16B Sep 2026 | IQ2_M | 189 GB | runs with 49 GB in system RAM | ~26 | ~25 | ~4,600 | |
| DeepSeek V4 Flash 284B-A13B Jul 2026 | IQ2_M | 98 GB | fits | 128K+ | ~200 | ~180 | ~11,000 |
| DeepSeek V3.1 671B-A37B Aug 2025 | Q4_K_M | 411 GB | does not fit | ||||
| Gemma | |||||||
| Gemma 4 12B May 2026 | Q8_0 | 14 GB | fits | 128K+ | ~240 | ~240 | ~12,000 |
| Gemma 4 31B Mar 2026 | Q8_0 | 35 GB | fits | 128K+ | ~94 | ~89 | ~4,800 |
| Gemma 4 26B-A4B Mar 2026 | Q8_0 | 28 GB | fits | 128K+ | ~210 | ~200 | ~38,000 |
| Gemma 3 27B Mar 2025 | Q8_0 | 31 GB | fits | 128K+ | ~100 | ~98 | ~5,300 |
| GLM | |||||||
| GLM-5.3 753B-A40B Aug 2026 | Q4_K_M | 462 GB | does not fit | ||||
| GLM-5.3 Flash 320B-A18B Aug 2026 | IQ2_M | 111 GB | fits | 128K+ | ~180 | ~170 | ~8,100 |
| GLM-4.6 355B-A32B Sep 2025 | IQ2_M | 125 GB | fits | 48K | ~130 | ~91 | ~4,600 |
| GLM-4.5 Air 106B-A12B Jul 2025 | Q8_0 | 115 GB | fits | 128K+ | ~120 | ~100 | ~12,000 |
| gpt-oss | |||||||
| gpt-oss-120b Aug 2025 | Q8_0 | 126 GB | fits | 128K+ | ~180 | ~170 | ~29,000 |
| gpt-oss-20b Aug 2025 | Q8_0 | 24 GB | fits | 128K+ | ~210 | ~190 | ~41,000 |
| Llama | |||||||
| Llama 4 Scout 109B-A17B Apr 2025 | Q8_0 | 119 GB | fits | 119K | ~100 | ~88 | ~8,600 |
| Llama 3.3 70B Dec 2024 | Q8_0 | 79 GB | fits | 128K+ | ~40 | ~36 | ~2,100 |
| Llama 3.1 8B Jul 2024 | Q8_0 | 11 GB | fits | 128K+ | ~330 | ~240 | ~18,000 |
| MiMo | |||||||
| MiMo V2.6 Pro 1.02T-A42B Sep 2026 | Q4_K_M | 624 GB | does not fit | ||||
| MiMo V2.6 Flash 309B-A15B Sep 2026 | IQ2_M | 107 GB | fits | 128K+ | ~190 | ~180 | ~9,700 |
| Mistral | |||||||
| Mistral Medium 3.5 128B Mar 2026 | Q8_0 | 140 GB | fits | 10K | ~23 | ~1,100 | |
| Mistral Small 4 119B-A6.5B Mar 2026 | Q8_0 | 132 GB | fits | 22K | ~140 | ~22,000 | |
| Mistral Small 3.2 24B Jun 2025 | Q8_0 | 28 GB | fits | 128K+ | ~120 | ~100 | ~6,100 |
| Nemotron | |||||||
| Nemotron 3.5 Lightning 30B-A3B Aug 2026 | Q8_0 | 35 GB | fits | 128K+ | ~210 | ~210 | ~42,000 |
| Qwen | |||||||
| Qwen3.8 Flash-Next 125B-A6B Aug 2026 | Q8_0 | 134 GB | fits | 128K+ | ~180 | ~170 | ~24,000 |
| Qwen3.8 27B Aug 2026 (your pick) | Q8_0 | 31 GB | fits | 128K+ | ~110 | ~100 | ~5,400 |
| Qwen3.6 27B Apr 2026 | Q8_0 | 31 GB | fits | 128K+ | ~110 | ~100 | ~5,400 |
| Qwen3.6 35B-A3B Apr 2026 | Q8_0 | 39 GB | fits | 128K+ | ~220 | ~210 | ~49,000 |
| Qwen3.5 9B Feb 2026 | Q8_0 | 11 GB | fits | 128K+ | ~320 | ~290 | ~16,000 |
| Qwen3 Coder 480B-A35B Jul 2025 | IQ2_M | 167 GB | runs with 26 GB in system RAM | ~19 | ~15 | ~2,100 | |
| Qwen3 235B-A22B Jul 2025 | Q3_K_M | 118 GB | fits | 123K | ~130 | ~110 | ~6,600 |
| Qwen3 32B Apr 2025 | Q8_0 | 38 GB | fits | 128K+ | ~85 | ~72 | ~4,500 |
Specifications
- Memory
- 141 GB HBM3e
- Memory bandwidth
- 4,800 GB/s
- Bus width
- 6144-bit
- Shader cores
- 16,896
- Tensor cores
- 528
- FP32
- 60.0 TFLOPS
- FP16 (dense)
- 835 TFLOPS
- FP8 (dense)
- 1671 TFLOPS
- Power
- 600 W
- Form factor
- Dual slot PCIe (NVL), passive, needs chassis airflow
- Interface
- PCIe 5.0 x16
- Architecture
- Hopper
- Launched
- 2024
Source: manufacturer specifications.