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

What LLMs can the RTX PRO 6000 Blackwell Workstation Edition run?

#	Model	Speed	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	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 244 t/s	244 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	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	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 244 t/s	244 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	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	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA 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	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 244 t/s	244 tok/s		Q4_K_M · 19.3 GB

#	Model	Speed ↓	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	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA 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	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

About the RTX PRO 6000 Blackwell Workstation Edition

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

RTX PRO 6000 Blackwell Workstation Edition tokens per second by model size

Output speed depends on memory bandwidth (1792 GB/s).

9BQwen3.5 9B · Q4_K_M · 6.6 GB
183tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
123tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
66.9tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
213tok/s
70BLlama 3.3 70B Instruct · Q4_K_M · 51.3 GB
25.0tok/s
120B MoEGPT OSS 120B · Q4_K_M · 70.8 GB
202tok/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 only

Best quant that fits, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with NVIDIA RTX PRO 6000 Blackwell Workstation Edition — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Tiny NemotronHForCausalLM Super4MChatFunctions Q4_K_M·116480.0 t/s	Q4_K_M	0.3 GB0%	116480.0 t/s	262K	S100, Runs great
Tiny NemotronHForCausalLM Ultra4MChatFunctions Q4_K_M·116480.0 t/s	Q4_K_M	0.3 GB0%	116480.0 t/s	262K	S100, Runs great
Pythia 160M213MChat Q4_K_M·8320.0 t/s	Q4_K_M	0.1 GB0%	8320.0 t/s	2K	S100, Runs great
DeepSeek v2 Lite Chat15.7BChat Q4_K_M·337.2 t/s	Q4_K_M	10.2 GB11%	337.2 t/s	164K	S100, Runs great
Llama 3.3 70B Instruct Abliterated70.6BChatFunctions Q4_K_M·26.9 t/s	Q4_K_M	48 GB50%	26.9 t/s	131K	A68, Runs well
Stable DiffCoder 8B Instruct8.3BChatCode BF16·68.2 t/s	BF16	17.9 GB19%	68.2 t/s	8K	S85, Runs great
HF Moshiko7.8BChat BF16·68.8 t/s	BF16	17.4 GB18%	68.8 t/s	3K	S85, Runs great
Nemotron Labs Diffusion 14B13.5BChat Q4_K_M·132.1 t/s	Q4_K_M	11.8 GB12%	132.1 t/s	262K	S95, Runs great
Mistral Small 24B Instruct 250123.6BChat Q4_K_M·78.4 t/s	Q4_K_M	17.8 GB19%	78.4 t/s	33K	S87, Runs great
Qwen2 VL 7B Instruct8.3BVision Q4_K_M·216.1 t/s	Q4_K_M	6.2 GB6%	216.1 t/s	33K	S100, Runs great
Qwen3 VL 4B Thinking4.4BVisionFunctions Q4_K_M·369.8 t/s	Q4_K_M	4.5 GB5%	369.8 t/s	262K	S100, Runs great
SILMA 9B Instruct v1.09.2BChat Q4_K_M·180.3 t/s	Q4_K_M	7.7 GB8%	180.3 t/s	8K	S99, Runs great
NVIDIA Nemotron 3 Super 120B A12B Base BF16123.6BChat Q4_K_M·86.3 t/s	Q4_K_M	74.7 GB78%	86.3 t/s	1049K	S88, Runs great
Nanonets OCR S3.8BVision Q4_K_M·442.9 t/s	Q4_K_M	3.2 GB3%	442.9 t/s	128K	S100, Runs great
EXAONE 3.5 7.8B Instruct7.8BChat Q4_K_M·225.7 t/s	Q4_K_M	7.7 GB8%	225.7 t/s	33K	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
Deploy

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	Q4_K_M	244 tok/s	$1.52$0.0078 input
GLM 4.7 Flash	Q4_K_M	196 tok/s	$1.89$0.015 input
Qwen3.8 27B	Q4_K_M	67 tok/s	$5.55$0.092 input
Muse Glimmer 30B	Q4_K_M	64 tok/s	$5.84$0.098 input
Gemma 4 31B IT	Q4_K_M	57 tok/s	$6.50$0.10 input

RTX PRO 6000 Blackwell Workstation Edition specs, power and PSU

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.

Best coding LLMs 48 GB VRAM GPUs with 96 GB or more RTX 5090 RTX 4090