A100 80GB vs RTX PRO 6000 Blackwell
The A100 80GB rents for 12% less per hour today — $1.79 against $2.05 — with 80 GB against 96 GB of memory.
Prices collected 2026-09-18 · 19 providers price both
Index median per GPU-hour, on-demand, per snapshot.
Side by side
| A100 80GB | RTX PRO 6000 Blackwell | |
|---|---|---|
| Median rental, per GPU-hour | $1.79 | $2.05 |
| Cheapest listing | $0.43 | $0.80 |
| Per month at 720 h | $1,289 | $1,472 |
| Providers pricing it | 37 | 24 |
| Memory | 80 GB HBM2e | 96 GB GDDR7 |
| Memory bandwidth | 2,039 GB/s | 1,792 GB/s |
| GB of memory per $/hr | 44.7 | 46.9 |
| Architecture | Ampere | Blackwell |
| Class | Datacenter | Workstation |
| Released | 2020-11 | 2025-04 |
Same provider, both GPUs
The cleanest comparison: 19 providers price both cards, so the difference is the GPU and nothing else. The A100 80GB is cheaper at 16 of them.
| Provider | A100 80GB | RTX PRO 6000 Blackwell | RTX PRO 6000 Blackwell premium |
|---|---|---|---|
 Vast.ai | $0.80 | $1.47 | +84% |
 Seeweb | $1.14 | $1.44 | +26% |
 GPU.ai | $1.21 | $1.84 | +52% |
 RunPod Community Cloud | $1.29 | $1.69 | +31% |
 io.net | $1.31 | $2.24 | +71% |
 Beam | $1.36 | $1.09 | -20% |
| $1.37 | $2.19 | +60% | |
 Hyperstack | $1.40 | $1.85 | +32% |
| $1.43 | $2.27 | +59% | |
 Runcrate | $1.49 | $2.41 | +62% |
 Jarvislabs | $1.49 | $1.89 | +27% |
 RunPod Secure Cloud | $1.59 | $2.14 | +35% |
 DataCrunch (Verda) | $1.74 | $1.90 | +9% |
 Northflank | $1.76 | $3.00 | +70% |
| $2.04 | $1.90 | -7% | |
 Cerebrium | $2.10 | $2.50 | +19% |
 Modal | $2.50 | $3.03 | +21% |
 CoreWeave | $2.70 | $2.50 | -7% |
 Oracle Cloud | $4.00 | $4.50 | +13% |
What each one runs, and what a million tokens costs
Weights + KV cache at 8K context + overhead against 90% of each card's memory. Where a model needs more than one card the cell says how many and prices the set at today's median. $/M tokens is the hourly median divided by estimated single-stream output, from memory bandwidth — an estimate for ranking, not a benchmark.
| Model | Bits | A100 80GB | RTX PRO 6000 Blackwell |
|---|---|---|---|
| Kimi K3 | 4-bit | 22× GPU$39.38/hr | 19× GPU$38.85/hr |
| Kimi K3 | 16-bit | 78× GPU$139.62/hr | 65× GPU$132.92/hr |
| DeepSeek V4.1-Flash | 4-bit | 5× GPU$8.95/hr | 4× GPU$8.18/hr |
| DeepSeek V4.1-Flash | 16-bit | 16× GPU$28.64/hr | 13× GPU$26.59/hr |
| Llama 4 Maverick | 4-bit | 4× GPU$7.16/hr | 3× GPU$6.14/hr |
| Llama 4 Maverick | 16-bit | 12× GPU$21.48/hr | 10× GPU$20.45/hr |
| gpt-oss-120b | 4-bit | ✓ 67.9 GB~569 tok/s · $0.87/M | ✓ 67.9 GB~500 tok/s · $1.14/M |
| gpt-oss-120b | 16-bit | 4× GPU$7.16/hr | 3× GPU$6.14/hr |
| Llama 3.1 70B | 4-bit | ✓ 44.5 GB~41 tok/s · $12.13/M | ✓ 44.5 GB~36 tok/s · $15.78/M |
| Llama 3.1 70B | 16-bit | 3× GPU$5.37/hr | 2× GPU$4.09/hr |
| Gemma 4 31B | 4-bit | ✓ 21.2 GB~94 tok/s · $5.29/M | ✓ 21.2 GB~82 tok/s · $6.93/M |
| Gemma 4 31B | 16-bit | ✓ 65.7 GB~26 tok/s · $19.12/M | ✓ 65.7 GB~23 tok/s · $24.7/M |
| Qwen3 Coder 30B-A3B | 4-bit | ✓ 19 GB~879 tok/s · $0.57/M | ✓ 19 GB~772 tok/s · $0.74/M |
| Qwen3 Coder 30B-A3B | 16-bit | ✓ 62.9 GB~247 tok/s · $2.01/M | ✓ 62.9 GB~217 tok/s · $2.62/M |
| Qwen3.8 27B | 4-bit | ✓ 18.7 GB~107 tok/s · $4.65/M | ✓ 18.7 GB~94 tok/s · $6.04/M |
| Qwen3.8 27B | 16-bit | ✓ 57.6 GB~30 tok/s · $16.57/M | ✓ 57.6 GB~27 tok/s · $21.04/M |
| gpt-oss-20b | 4-bit | ✓ 13.7 GB~806 tok/s · $0.62/M | ✓ 13.7 GB~708 tok/s · $0.8/M |
| gpt-oss-20b | 16-bit | ✓ 43.9 GB~227 tok/s · $2.19/M | ✓ 43.9 GB~199 tok/s · $2.85/M |
| Llama 3.1 8B | 4-bit | ✓ 6.9 GB~362 tok/s · $1.37/M | ✓ 6.9 GB~319 tok/s · $1.78/M |
| Llama 3.1 8B | 16-bit | ✓ 18.4 GB~102 tok/s · $4.87/M | ✓ 18.4 GB~90 tok/s · $6.31/M |
Buy or rent?
Hours of renting at today's median that add up to the card's approximate list price. List prices are typical quoted figures, not tracked, and do not include the server, power or the person to run it — so the break-even is a floor, not a verdict.
Questions
Is the A100 80GB or the RTX PRO 6000 Blackwell cheaper to rent?
On 2026-09-18 the A100 80GB has a market median of $1.79 per GPU-hour across 37 providers and the RTX PRO 6000 Blackwell $2.04 across 24, so the A100 80GB is 12% cheaper per hour. Among the 19 providers that price both, the A100 80GB is cheaper at 16 and the RTX PRO 6000 Blackwell at 3. Per hour is only half the answer — the table below prices a whole model on each.
Which should I rent for a 70B model?
At 4-bit, Llama 3.1 70B needs about 44.5 GB. On the A100 80GB that is one card at $1.79/hr; on the RTX PRO 6000 Blackwell one card at $2.05/hr. Estimated single-stream decode is ~41 vs ~36 tokens per second, from memory bandwidth.
What is the real difference between them?
80 GB HBM2e at 2,039 GB/s (Ampere) against 96 GB GDDR7 at 1,792 GB/s (Blackwell). Memory decides what fits; bandwidth decides how fast it generates, because each token streams the active weights once. Compute matters for prompt processing and training, not for how fast text appears.