RTX Pro 6000 Blackwell for local LLMs
9 measured results from 3 builds, each linked to its source.
| Memory | 96 GB per card |
|---|---|
| Memory bandwidth | not listed |
| Typical EU price | ≈€16,885 new (PNY Quadro RTX Pro 6000 Blackwell 96 GB GDDR7, billiger.de, 2026-10-24) |
Can it run? Qwen3.8 27B on RTX Pro 6000 Max-Q (Blackwell, 96 GB, 300 W) gpt-oss 120B on RTX Pro 6000 (Blackwell, 96 GB) gpt-oss 20B on RTX Pro 6000 (Blackwell, 96 GB)
All builds with the RTX Pro 6000 Blackwell
| Build | GPU(s) | Memory GB (total) | Results |
|---|---|---|---|
| EPYC 7532 workstation (RTX Pro 6000 + RTX 3090 Ti, 300 W caps): Qwen3.8-Flash-Next, llama.cpp vs Strata engine | RTX Pro 6000 Blackwell Workstation (96 GB) + RTX 3090 Ti (EVGA FTW3 Ultra, 24 GB); each test used one card | 120 | 5 |
| RTX Pro 6000 96GB workstation card | RTX Pro 6000 (Blackwell) | 96 | 2 |
| RTX Pro 6000 Blackwell Max-Q (300 W cap): Qwen3.8 27B on vLLM, NVFP4 vs BF16 | RTX Pro 6000 Max-Q (Blackwell, 96 GB) | 96 | 2 |
All measured results
(MTP, DFlash, DSpark and similar draft-and-verify methods give much higher tok/s on predictable text and are not comparable 1:1 with plain decode)
| Model | Build | Ran on | Quant | Engine | tok/s | Details |
|---|---|---|---|---|---|---|
| Qwen3.8 27B | RTX Pro 6000 Blackwell Max-Q (300 W cap): Qwen3.8 27B on vLLM, NVFP4 vs BF16 | RTX Pro 6000 Max-Q (Blackwell, 96 GB, 300 W) | NVFP4 (W4A16) + MTP (5 draft tokens), 256K context | vLLM 0.27.1 | 150 | ⚡ spec-decode (MTP) |
| Qwen3.8 27B | RTX Pro 6000 Blackwell Max-Q (300 W cap): Qwen3.8 27B on vLLM, NVFP4 vs BF16 | RTX Pro 6000 Max-Q (Blackwell, 96 GB, 300 W) | BF16 + MTP (5 draft tokens), 256K context | vLLM 0.20.1 | 85 | ⚡ spec-decode (MTP) |
| Qwen3.8 Flash-Next | EPYC 7532 workstation (RTX Pro 6000 + RTX 3090 Ti, 300 W caps): Qwen3.8-Flash-Next, llama.cpp vs Strata engine | mixed / see build | IQ3_S + model draft head, all experts on the RTX Pro 6000 | Strata engine 0.1.39, RTX Pro 6000 | 205.263 | ⚡ spec-decode (speculative) |
| Qwen3.8 Flash-Next | EPYC 7532 workstation (RTX Pro 6000 + RTX 3090 Ti, 300 W caps): Qwen3.8-Flash-Next, llama.cpp vs Strata engine | mixed / see build | IQ3_S, all experts on the RTX Pro 6000, no draft head | llama.cpp (3cf03257), RTX Pro 6000 | 102.889 | ⚡ spec-decode (speculative) |
| Qwen3.8 Flash-Next | EPYC 7532 workstation (RTX Pro 6000 + RTX 3090 Ti, 300 W caps): Qwen3.8-Flash-Next, llama.cpp vs Strata engine | mixed / see build | IQ3_S + draft head, 8,144 of 24,576 experts on card | Strata engine 0.1.39, RTX 3090 Ti | 98.291 | ⚡ spec-decode (speculative) |
| Qwen3.8 Flash-Next | EPYC 7532 workstation (RTX Pro 6000 + RTX 3090 Ti, 300 W caps): Qwen3.8-Flash-Next, llama.cpp vs Strata engine | mixed / see build | IQ3_S, 32K prompt, all on the RTX Pro 6000 | llama.cpp (3cf03257), RTX Pro 6000 | 76.337 | |
| Qwen3.8 Flash-Next | EPYC 7532 workstation (RTX Pro 6000 + RTX 3090 Ti, 300 W caps): Qwen3.8-Flash-Next, llama.cpp vs Strata engine | mixed / see build | IQ3_S, experts of 34/48 layers in system RAM, no draft head | llama.cpp (b11514), RTX 3090 Ti | 22.657 | ⚡ spec-decode (speculative) |
| gpt-oss 120B | RTX Pro 6000 96GB workstation card | RTX Pro 6000 (Blackwell, 96 GB) | MXFP4 | llama.cpp | 196.31 | |
| gpt-oss 20B | RTX Pro 6000 96GB workstation card | RTX Pro 6000 (Blackwell, 96 GB) | MXFP4 | llama.cpp | 286.91 |
All RTX Pro 6000 Blackwell builds: see also all GPUs · best LLMs by memory size · download the dataset.
FAQ
How fast is the RTX Pro 6000 Blackwell for local LLMs?
The fastest plain-decode result we have is 286.91 tok/s on gpt-oss 20B (MXFP4, llama.cpp) in RTX Pro 6000 96GB workstation card. Speed depends heavily on the model, quant and engine, so compare like with like in the table. RigBase lists 9 measured results from 3 builds.
How much memory does the RTX Pro 6000 Blackwell have?
96 GB per card.
Which models have been measured on the RTX Pro 6000 Blackwell?
Qwen3.8 27B, Qwen3.8 Flash-Next, gpt-oss 120B, gpt-oss 20B.
Where do these numbers come from?
Every row links to a build page with its original public source (benchmark logs, READMEs, forum posts). RigBase does not re-run the benchmarks. Results marked ⚡ use speculative decoding and are not comparable 1:1 with plain decode.
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.