NVIDIA RTX PRO 6000 Blackwell Max-Q 96GB
96GB VRAM
/
1792 GB/s
/
300W
/
$8,565 MSRP
/
Released 2025
Overview
NVIDIA’s workstation Blackwell card: 96GB GDDR7 ECC at 1,792 GB/s, 2025, $8,565 MSRP - and it shares the RTX 5090’s bandwidth number while carrying three times the memory. Two variants on this site: the 600W standard card and the 300W Max-Q (same memory, same bandwidth, lower clocks and price of admission to your PSU).
What it does well:
- 96GB single-slot capacity: 70B dense at 8-bit, 235B-class MoE at 4-bit, in one card with full CUDA - the largest-memory single GPU on this site that runs the standard consumer runtime stack.
- Server-grade memory: ECC GDDR7 and datacenter driver support, in a dual-slot card a workstation can hold.
Where it falls short: $8,565 MSRP is 4.3x a 5090 for the same bandwidth - you are paying for the memory, not speed. Street prices above MSRP have been the norm since launch.
Run it locally: full CUDA stack - llama.cpp, Ollama, vLLM. The modeldex results rank checkpoints by fit and estimated tok/s.
Chip specs
- Nvidia RTX PRO 6000 Blackwell Max-Q
- 96GB vram
- 1792 GB/s
- 2025
- Not specified
Top models (110 compatible)
GLM-5.3-Flash
UD-IQ1_S
Runs with CPU offload
93.1GB / 100.0GB min
188
ⓘ estimated
Qwen3.8-Flash-Next
EXL3_2BPW
Runs comfortably
62.7GB / 24.0GB min
471
ⓘ estimated
Qwen3.6 35B A3B
Q4_K_M
Runs comfortably
20.0GB / 20.0GB min
574
ⓘ estimated
Ornith-1.5-35B-A3B
Q4_K_M
Runs comfortably
21.7GB / 22.0GB min
544
ⓘ estimated
Pokee-Isaac 28B
Q4_K_M
Runs comfortably
16.0GB / 18.0GB min
62
ⓘ estimated