← All GPUs
NVIDIA · Workstation · Blackwell (GB202)
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
Same 96 GB as the Workstation Edition at half the power; NVIDIA says it scales from one to four GPUs in one workstation.
VRAM
96 GB
GDDR7 ECC
Memory bandwidth
1,792 GB/s
FP16 compute
not published
Price
No list price
What fits at 4-bit
The 4-bit file plus 8,192 tokens of context and 1.5 GB of overhead, against the VRAM of one card. Speeds are measured medians where someone has published a run at that card count; a blank speed means no run, not a slow one. Machine pages carry estimates for the gaps.
| Model | Needs | 1 card (96 GB) |
|---|---|---|
| Qwen3.5 4B4B · Q4_K_M | 4.3 GB | fits |
| Llama 3.1 8B Instruct8B · Q4_K_M | 7.1 GB | 46 tok/smedian of 1 run |
| Qwen3 8B8.2B · Q4_K_M | 7.3 GB | fits |
| Gemma 4 E4B IT8B · Q4_K_M | 6.5 GB | fits |
| Granite 4.2 8B8.8B · Q4_K_M | 7.9 GB | fits |
| Qwen3.5 9B9B · Q4_K_M | 7.0 GB | fits |
| Gemma 4 12B IT11.95B · Q4_K_M | 8.2 GB | fits |
| Ministral 3 14B Reasoning (2512)13.9B · Q4_K_M | 10.4 GB | fits |
| Phi-414.7B · Q4_K_M | 11.3 GB | fits |
| gpt-oss-20b21B, 3.6B active · MXFP4 (native) | 12.5 GB | 250 tok/smedian of 1 run |
| Devstral Small 2 24B (2512)24B · Q4_K_M | 16.1 GB | fits |
| Qwen3.6 27B27B · Q4_K_M | 17.7 GB | fits |
| Gemma 4 26B-A4B IT25.2B, 3.8B active · Q4_K_M | 17.4 GB | fits |
| Qwen3.8 27B27B · Q4_K_M | 18.2 GB | fits |
| Granite 4.2 30B29.3B · Q4_K_M | 20.3 GB | fits |
| Gemma 4 31B IT30.7B · Q4_K_M | 18.9 GB | fits |
| Qwen3 Coder 30B-A3B Instruct30.5B, 3.3B active · Q4_K_M | 19.5 GB | fits |
| Ornith 1.5 35B-A3B35B, 3B active · Q4_K_M | 21.9 GB | fits |
| Qwen3.6 35B-A3B35B, 3B active · Q4_K_M | 22.4 GB | fits |
| Nemotron 3.5 Lightning 30B-A3B30B, 3B active · Q4_K_M | 25.3 GB | fits |
| Llama 3.3 70B Instruct70B · Q4_K_M | 43.6 GB | fits |
| Qwen3 Coder Next80B, 3B active · Q4_K_M | 46.9 GB | fits |
| gpt-oss-120b117B, 5.1B active · MXFP4 (native) | 60.2 GB | 184 tok/smedian of 2 runs |
| Llama 4 Scout 17B-16E Instruct109B, 17B active · Q4_K_M | 62.4 GB | fits |
| Mistral Small 4 119B (2603)119B, 6.5B active · Q4_K_M | 69.3 GB | fits |
| GLM-4.5-Air106B, 12B active · Q4_K_M | 70.9 GB | fits |
| Mistral Medium 3.5 128B128B · Q4_K_M | 74.0 GB | fits |
| Qwen3.5 122B-A10B122B, 10B active · Q4_K_M | 73.0 GB | fits |
| Nemotron 3 Super 120B-A12B120B, 12B active · Q4_K_M | 82.6 GB | fits |
Measured speeds
One card
| Model | Quant | Backend | Generation | Prompt | Context | Source |
|---|---|---|---|---|---|---|
| gpt-oss-120b | MXFP4 MoE | llama.cpp b6445 CUDA | 197 tok/s | 6,404 tok/s2,048-token prompt | 0 | llama.cpp benchmark discussion2025-09 |
| gpt-oss-120b | MXFP4 MoE | llama.cpp b6199 CUDA | 171 tok/s | 4,494 tok/s2,048-token prompt | 0 | llama.cpp benchmark discussion2025-08 |
| gpt-oss-20b | MXFP4 MoE | llama.cpp b6199 CUDA | 250 tok/s | 9,481 tok/s2,048-token prompt | 0 | llama.cpp benchmark discussion2025-08 |
| Llama 3.1 8B Instruct | Q4_K_M | LocalScore (llamafile; version not stated) | 46 tok/s | 5,544 tok/s | 0 | LocalScore2026-10 |
Specifications
- Memory
- 96 GB GDDR7 ECC
- FP16 basis
- NVIDIA publishes 3,511 AI TOPS (FP4 with sparsity) and 110 TFLOPS FP32; no dense FP16 tensor figure.
- Board power
- 300 W
- Slots
- 2
- Length
- 267 mm
- PCIe
- Gen 5 x16
- NVLink
- No
- Cooling
- Blower
- Software
- CUDA, Vulkan
- Released
- 2025
- Availability
- sold new
- Price basis
- No NVIDIA list price found; NVIDIA's store could not be loaded from our tooling.
- Maker page
- nvidia.com
Sources
- nvidia.com: datasheet: 96 GB GDDR7 ECC, 1792 GB/s, PCIe 5.0 x16, 300 W, 4.4 x 10.5 in dual slot, active thermal, 3511 AI TOPS FP4 sparse
- nvidia.com: 'scale from one to four GPUs'