NVIDIA · Blackwell
Best AI Models for NVIDIA RTX PRO 6000 Blackwell Workstation Edition (96 GB)
Runs everything up to 120B MoE well.
96 GB GDDR71792 GB/s500 TFLOPS FP16600 WBlackwell 2025
| # | Model | Speed | llmrun Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 66.9 t/s | 66.9 tok/s | Q4_K_M · 17.9 GB | |
| 2 | Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 66.9 t/s | 66.9 tok/s | Q4_K_M · 17.9 GB | |
| 3 | Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 57.1 t/s | 57.1 tok/s | Q4_K_M · 21.7 GB | |
| 4 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 250 t/s | 250 tok/s | Q4_K_M · 16.5 GB | |
| 5 | Q4_K_M · 19.3 GB · 244 t/s | 244 tok/s | Q4_K_M · 19.3 GB |
| # | Model | Speed | Coding Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 66.9 t/s | 66.9 tok/s | Q4_K_M · 17.9 GB | |
| 2 | Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 57.1 t/s | 57.1 tok/s | Q4_K_M · 21.7 GB | |
| 3 | Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 213 t/s | 213 tok/s | Q4_K_M · 22.0 GB | |
| 4 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 250 t/s | 250 tok/s | Q4_K_M · 16.5 GB | |
| 5 | Q4_K_M · 19.3 GB · 244 t/s | 244 tok/s | Q4_K_M · 19.3 GB |
| # | Model | Speed | Reasoning Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 66.9 t/s | 66.9 tok/s | Q4_K_M · 17.9 GB | |
| 2 | Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 57.1 t/s | 57.1 tok/s | Q4_K_M · 21.7 GB | |
| 3 | Qwen3.5 27BAlibaba Q4_K_M · 17.9 GB · 66.9 t/s | 66.9 tok/s | Q4_K_M · 17.9 GB | |
| 4 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 250 t/s | 250 tok/s | Q4_K_M · 16.5 GB | |
| 5 | Q4_K_M · 19.3 GB · 244 t/s | 244 tok/s | Q4_K_M · 19.3 GB |
| # | Model | Speed | Math Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 66.9 t/s | 66.9 tok/s | Q4_K_M · 17.9 GB | |
| 2 | Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 66.9 t/s | 66.9 tok/s | Q4_K_M · 17.9 GB | |
| 3 | Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 213 t/s | 213 tok/s | Q4_K_M · 22.0 GB | |
| 4 | Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 57.1 t/s | 57.1 tok/s | overall | Q4_K_M · 21.7 GB |
| 5 | Q4_K_M · 19.3 GB · 244 t/s | 244 tok/s | Q4_K_M · 19.3 GB |
| # | Model | Speed ↓ | llmrun Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 357 t/s | 357 tok/s | Q4_K_M · 3.4 GB | |
| 2 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 282 t/s | 282 tok/s | Q4_K_M · 13.1 GB | |
| 3 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 250 t/s | 250 tok/s | Q4_K_M · 16.5 GB | |
| 4 | Q4_K_M · 19.3 GB · 244 t/s | 244 tok/s | Q4_K_M · 19.3 GB | |
| 5 | Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 227 t/s | 227 tok/s | Q4_K_M · 19.4 GB |
| # | Model | Speed | Vision Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 66.9 t/s | 66.9 tok/s | Q4_K_M · 17.9 GB | |
| 2 | Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 66.9 t/s | 66.9 tok/s | Q4_K_M · 17.9 GB | |
| 3 | Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 57.1 t/s | 57.1 tok/s | Q4_K_M · 21.7 GB | |
| 4 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 250 t/s | 250 tok/s | Q4_K_M · 16.5 GB | |
| 5 | JEV 27B VLautotrust Q4_K_M · 17.9 GB · 66.9 t/s | 66.9 tok/s | Q4_K_M · 17.9 GB |
See all 391 models on the RTX PRO 6000 Blackwell Workstation Edition →Best quant that fits · speeds estimated on this card
The RTX PRO 6000 Blackwell Workstation Edition runs everything up to 120B MoE well. Blackwell generation, released 2025.
GenerationBlackwellreleased 2025
RTX PRO 6000 Blackwell Workstation Edition strengths and weaknesses
Strengths
- Runs 120B MoE models: GPT OSS 120B at 202 tok/s in 70.8 GB
- Room for long context: Llama 3.3 70B Instruct at Q4 uses 51.3 GB, leaving 44.7 GB free
- Reads long prompts fast: A 4K-token prompt on Qwen3.8 27B starts answering in 1.0 s
- FP8 and NVFP4 run natively: Blackwell takes FP8 and NVFP4 checkpoints in vLLM as published
Weaknesses
- 600 W under load: Plan a 1,200 W PSU; ≈$131 a year at 4 h a day
Output speed depends on memory bandwidth (1792 GB/s).
- 9BQwen3.5 9B · Q4_K_M · 6.6 GB183tok/s
- 14BQwen3 14B · Q4_K_M · 11.9 GB123tok/s
- 27–31BQwen3.8 27B · Q4_K_M · 17.9 GB66.9tok/s
- 35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB213tok/s
- 70BLlama 3.3 70B Instruct · Q4_K_M · 51.3 GB25.0tok/s
- 120B MoEGPT OSS 120B · Q4_K_M · 70.8 GB202tok/s
Estimated speeds: Q4_K_M, 4K context, one user. How we estimate
All 1270 models on the RTX PRO 6000 Blackwell Workstation Edition
Featured onlyBest quant that fits, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works
| Model | Quant | VRAM | Speed | Context | Score | Fit |
|---|---|---|---|---|---|---|
Yi 1.5 6B ChatChat | Q4_K_M | 4.2 GB | 286.2 t/s | 4K | S100, Runs great | |
Tiny Random Phi3Chat | Q4_K_M | 0.3 GB | 3882.7 t/s | 4K | S100, Runs great | |
Aya Expanse 8BChat | BF16 | 20.2 GB | 66.0 t/s | — | S85, Runs great | |
NuExtract 1.5Chat | Q4_K_M | 9.0 GB | 342.6 t/s | 131K | S100, Runs great | |
Tiny MixtralChat | Q4_K_M | 0.5 GB | 3452.4 t/s | 131K | S100, Runs great | |
Gemma 4 12BChat | Q4_K_M | 9.0 GB | 141.5 t/s | 262K | S96, Runs great | |
| BF16 | 19.6 GB | 66.3 t/s | 262K | S85, Runs great | ||
| Q4_K_M | 1.7 GB | 1338.9 t/s | 33K | S100, Runs great | ||
| Q4_K_M | 6.2 GB | 216.1 t/s | 8K | S100, Runs great | ||
Supra 50M BaseChat | Q4_K_M | 0.3 GB | 3235.6 t/s | 1K | S100, Runs great | |
Granite 4.0 MicroChatFunctions | Q4_K_M | 3.7 GB | 464.1 t/s | 131K | S100, Runs great | |
LFM2.5 1.2B InstructChatFunctions | Q4_K_M | 1.2 GB | 1088.6 t/s | 128K | S100, Runs great | |
Llama 3.2 11B Vision InstructVisionFunctions | Q4_K_M | 9.8 GB | 165.5 t/s | — | S98, Runs great | |
Distilgpt2Chat | Q4_K_M | 0.1 GB | 19413.3 t/s | 1K | S100, Runs great | |
Gemma 4 E2BChat | Q4_K_M | 3.5 GB | 339.6 t/s | 131K | S100, Runs great |
Rent NVIDIA RTX PRO 6000 Blackwell Workstation Edition in the cloud
Hourly rate on demand for one RTX PRO 6000 Blackwell Workstation Edition.
Vast.aiMarketplace
from$1.34/hr
Buying one ($8,565) costs as much as ~6,400 hours of rental, about 27 months at 8 hours a day.
Cost per million tokens
Output-token cost on an RTX PRO 6000 Blackwell Workstation Edition rented at $1.34/hr, one request at a time. Batch several users on the same card and the cost per token drops several-fold.
| Model | Quant | Speed | Per 1M output |
|---|---|---|---|
| NVIDIA Nemotron 3.5 Lightning 30B A3B BF16 | 244 tok/s | $1.52$0.0078 input | |
| GLM 4.7 Flash | 196 tok/s | $1.89$0.015 input | |
| Qwen3.8 27B | 67 tok/s | $5.55$0.092 input | |
| Muse Glimmer 30B | 64 tok/s | $5.84$0.098 input | |
| Gemma 4 31B IT | 57 tok/s | $6.50$0.10 input |
Specs
- Architecture
- Blackwell
- VRAM
- 96 GB GDDR7
- Memory bandwidth
- 1792.0 GB/s
- FP16 (dense)
- 500.00 TFLOPS
- CUDA cores
- 24,064
- Tensor cores
- 752
- Compute capability
- 12.0
- TDP
- 600 W
- Released
- 2025-04-01
- MSRP
- $8,565
RTX PRO 6000 Blackwell Workstation Edition FAQ
What is the largest model the RTX PRO 6000 Blackwell Workstation Edition can run?
Mistral Medium 3.5 128B (127.7B) is the largest at 4-bit or better: at Q4_K_M it uses 82.8 GB of 96 GB, and runs at about 15.0 tok/s.
Can the RTX PRO 6000 Blackwell Workstation Edition run Qwen3.8 27B?
Yes. Qwen3.8 27B fits at Q4_K_M, using 17.9 GB of 96 GB, and it is the best model that runs well on this card.
How many tokens per second does the RTX PRO 6000 Blackwell Workstation Edition give?
About 66.9 tok/s on Qwen3.8 27B at Q4_K_M, with the first token after 1.0 s on a 4K-token prompt.
What power supply does the RTX PRO 6000 Blackwell Workstation Edition need?
Plan a 1200 W PSU (2× the 600 W TDP).
Is 96 GB enough for coding and agents?
Yes for coding: Qwen3.8 27B, the best of the 14 coding models that fit, runs at about 67 tok/s.