RTX PRO 6000 Blackwell Max-Q Workstation Edition
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition: 96 GB of memory at 1792 GB/s. Below: the open models it can run, estimated at 96 GB with an 8K context. The 300 W blower version of the RTX PRO 6000: the same 96 GB at 1,792 GB/s, built to stack two to four cards in one tower.
Last updated: 2026-10-16
Specifications
What it can run
Best-quality quantization that fits with a 8K context, and the estimated generation speed. Estimates, not benchmarks. See the methodology.
| Model | Params | Best quant | Memory | tok/s (est.) |
|---|---|---|---|---|
| Qwen3.5-122B-A10B | 122B (10B) | Q5_K_M | 85.5 GiB | 130 |
| Mistral Small 4 119B (2603) | 119B (6.5B) | Q5_K_M | 83.4 GiB | 176 |
| gpt-oss-120b | 117B (5.1B) | Q6_K | 95.0 GiB | 187 |
| Llama 4 Scout 17B-16E Instruct | 109B (17B) | Q6_K | 89.8 GiB | 76 |
| GLM-4.5-Air | 106B (12B) | Q6_K | 87.3 GiB | 101 |
| Qwen3-Coder-Next (80B-A3B) | 80B (3B) | Q8_0 | 83.8 GiB | 220 |
| Llama 3.3 70B Instruct | 70B | Q8_0 | 75.7 GiB | 16 |
| Qwen3.5-35B-A3B | 35B (3B) | FP16 | 69.1 GiB | 147 |
| Qwen3.6-35B-A3B | 35B (3B) | FP16 | 69.1 GiB | 147 |
| Qwen3-32B | 32.8B | FP16 | 66.6 GiB | 18 |
| DeepSeek-R1-Distill-Qwen-32B | 32.76B | FP16 | 66.6 GiB | 18 |
| Gemma 4 31B IT | 30.7B | FP16 | 61.6 GiB | 20 |
| Qwen3-30B-A3B (2507) | 30.5B (3.3B) | FP16 | 60.9 GiB | 138 |
| Qwen3-Coder-30B-A3B-Instruct | 30.5B (3.3B) | FP16 | 60.9 GiB | 138 |
| GLM-4.7-Flash (30B-A3B) | 30B (3B) | FP16 | 59.6 GiB | 147 |
| Qwen3.5-27B | 27B | FP16 | 53.8 GiB | 22 |
| Qwen3.6-27B | 27B | FP16 | 53.8 GiB | 22 |
| Qwen3.8-27B | 27B | FP16 | 53.8 GiB | 22 |
| Gemma 3 27B IT | 27B | FP16 | 54.3 GiB | 22 |
| Gemma 4 26B A4B IT | 25.2B (3.8B) | FP16 | 50.1 GiB | 124 |
| Mistral Small 3.2 24B Instruct (2506) | 24B | FP16 | 48.7 GiB | 25 |
| Magistral Small 1.2 (2509) | 24B | FP16 | 48.7 GiB | 25 |
| Devstral Small 2 24B Instruct (2512) | 24B | FP16 | 48.7 GiB | 25 |
| gpt-oss-20b | 21B (3.6B) | FP16 | 41.8 GiB | 129 |
| Phi-4 (14B) | 14B | FP16 | 29.4 GiB | 41 |
| Gemma 3 12B IT | 12B | FP16 | 24.8 GiB | 47 |
| Gemma 4 12B Unified IT | 11.95B | FP16 | 24.2 GiB | 47 |
| Qwen3.5-9B | 9B | FP16 | 18.4 GiB | 61 |
| Qwen3-8B | 8.2B | FP16 | 17.7 GiB | 66 |
| DeepSeek-R1-0528-Qwen3-8B | 8.19B | FP16 | 17.6 GiB | 66 |
| Llama 3.1 8B Instruct | 8B | FP16 | 17.1 GiB | 68 |
| Gemma 4 E4B IT | 8B | FP16 | 16.4 GiB | 68 |
| Llama 3.2 3B Instruct | 3.21B | FP16 | 7.7 GiB | 140 |
| Kimi K2.6 | 1000B (32B) | Doesn't fit | – | – |
| DeepSeek-R1-0528 (671B) | 671B (37B) | Doesn't fit | – | – |
| DeepSeek-V4-Flash | 284B (13B) | Doesn't fit | – | – |
| Qwen3.8-Flash-Next | 180B (6B) | Doesn't fit | – | – |
Prices
Latest price at each shop, as listed on the day we checked.
| Region | Shop | Listing | Price | Per GB | Checked |
|---|---|---|---|---|---|
| Taiwan | 原價屋 CoolPC | Leadtek RTX PRO 6000 Blackwell Max-Q 96GBLine on the shop's public price list (no per-product page); list stamped 2026/10/15 9:31 | NT$575,000 | NT$5,990/GB | 2026-10-15 |
- Taiwan value: about 170.5 tok/s on Llama 3.1 8B Instruct (Q4_K_M, 8K), or 0.3 tok/s per NT$1,000.
A price history chart appears once we have checked this device on two or more days.
All prices →Frequently asked questions
Which LLMs can the RTX PRO 6000 Blackwell Max-Q Workstation Edition run?
With 96 GB and an 8K context, the largest models that fit include: Qwen3.5-122B-A10B, Mistral Small 4 119B (2603), gpt-oss-120b, Llama 4 Scout 17B-16E Instruct, GLM-4.5-Air. See the full table below.
How fast is the RTX PRO 6000 Blackwell Max-Q Workstation Edition for local LLMs?
Generation speed is mostly set by memory bandwidth (1792 GB/s). For Llama 3.1 8B Instruct at FP16, expect roughly 68 tokens/s; bigger models are slower.
Can the RTX PRO 6000 Blackwell Max-Q Workstation Edition run 70B models?
Yes. Llama 3.3 70B Instruct fits on the RTX PRO 6000 Blackwell Max-Q Workstation Edition (96 GB) at Q8_0 with an 8K context, using about 75.7 GiB, at an estimated 16 tokens/s.