NVIDIA · Blackwell

Best AI Models for NVIDIA RTX PRO 6000 Blackwell Server Edition (96 GB)

Runs everything up to 120B MoE well.

96 GB GDDR71597 GB/s500 TFLOPS FP16600 WBlackwell 2025

Passive 96 GB server variant — needs chassis airflow; commonly rented per-GPU rather than bought for a desktop.

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

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 59.6 t/s	59.6 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 59.6 t/s	59.6 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 50.9 t/s	50.9 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 233 t/s	233 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 235 t/s	235 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 59.6 t/s	59.6 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 50.9 t/s	50.9 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 200 t/s	200 tok/s	Q4_K_M · 22.0 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 233 t/s	233 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 235 t/s	235 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 59.6 t/s	59.6 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 50.9 t/s	50.9 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.5 27BAlibaba Q4_K_M · 17.9 GB · 59.6 t/s	59.6 tok/s	Q4_K_M · 17.9 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 233 t/s	233 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 235 t/s	235 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 · 59.6 t/s	59.6 tok/s		Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 59.6 t/s	59.6 tok/s		Q4_K_M · 17.9 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 200 t/s	200 tok/s		Q4_K_M · 22.0 GB
4	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 50.9 t/s	50.9 tok/s	overall	Q4_K_M · 21.7 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 235 t/s	235 tok/s		Q4_K_M · 19.3 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 318 t/s	318 tok/s	Q4_K_M · 3.4 GB
2	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 262 t/s	262 tok/s	Q4_K_M · 13.1 GB
3	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 235 t/s	235 tok/s	Q4_K_M · 19.3 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 233 t/s	233 tok/s	Q4_K_M · 16.5 GB
5	Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 216 t/s	216 tok/s	Q4_K_M · 19.4 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 59.6 t/s	59.6 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 59.6 t/s	59.6 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 50.9 t/s	50.9 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 233 t/s	233 tok/s	Q4_K_M · 16.5 GB
5	JEV 27B VLautotrust Q4_K_M · 17.9 GB · 59.6 t/s	59.6 tok/s	Q4_K_M · 17.9 GB

See all 391 models on the RTX PRO 6000 Blackwell Server Edition →Best quant that fits · speeds estimated on this card

About the RTX PRO 6000 Blackwell Server Edition

The RTX PRO 6000 Blackwell Server Edition runs everything up to 120B MoE well. Blackwell generation, released 2025.

GenerationBlackwellreleased 2025

RTX PRO 6000 Blackwell Server Edition strengths and weaknesses

Strengths

Runs 120B MoE models: GPT OSS 120B at 188 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 Server Edition tokens per second by model size

Output speed depends on memory bandwidth (1597 GB/s).

9BQwen3.5 9B · Q4_K_M · 6.6 GB
163tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
109tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
59.6tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
200tok/s
70BLlama 3.3 70B Instruct · Q4_K_M · 51.3 GB
22.3tok/s
120B MoEGPT OSS 120B · Q4_K_M · 70.8 GB
188tok/s

Estimated speeds: Q4_K_M, 4K context, one user. How we estimate

All 1270 models on the RTX PRO 6000 Blackwell Server 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 Server Edition — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Opt 125M125MChat FP16·3707.3 t/s	FP16	0.3 GB0%	3707.3 t/s	2K	S100, Runs great
Qwen3 VL 2B Thinking2.1BVisionFunctions Q4_K_M·573.5 t/s	Q4_K_M	3.5 GB4%	573.5 t/s	262K	S100, Runs great
Qwen2.5 VL 72B Instruct73.4BVision Q4_K_M·23.1 t/s	Q4_K_M	49.7 GB52%	23.1 t/s	128K	B64, Decent
Ministral 8B Instruct 24108.0BChatFunctions Q4_K_M·191.9 t/s	Q4_K_M	7.5 GB8%	191.9 t/s	33K	S99, Runs great
NVIDIA Nemotron Nano 12B v212.3BChatFunctions Q4_K_M·127.8 t/s	Q4_K_M	11.0 GB11%	127.8 t/s	—	S95, Runs great
NVIDIA Nemotron Nano 9B v2 Japanese8.9BChat Q4_K_M·171.9 t/s	Q4_K_M	6.0 GB6%	171.9 t/s	131K	S98, Runs great
Tiny NemotronHForCausalLM Nano4MChatFunctions Q4_K_M·103805.0 t/s	Q4_K_M	0.3 GB0%	103805.0 t/s	262K	S100, Runs great
Qwen3.6 27B DFlash27BChat Q4_K_M·62.7 t/s	Q4_K_M	16.9 GB18%	62.7 t/s	262K	A84, Runs well
Qwen3.5 2B Base2.3BVision Q4_K_M·586.5 t/s	Q4_K_M	1.9 GB2%	586.5 t/s	262K	S100, Runs great
Transformer 1.3B 100B1.4BChat BF16·346.0 t/s	BF16	3 GB3%	346.0 t/s	2K	S100, Runs great
Gemma 3 270M IT268MChat Q4_K_M·5766.9 t/s	Q4_K_M	1.2 GB1%	5766.9 t/s	—	S100, Runs great
Instella 3B3.1BChat BF16·142.6 t/s	BF16	8.0 GB8%	142.6 t/s	4K	S96, Runs great
Hermes 3 Llama 3.1 70B70.6BChatRoleplay Q4_K_M·24.0 t/s	Q4_K_M	48 GB50%	24.0 t/s	131K	B64, Decent
Tiny NemotronHForCausalLM Super4MChatFunctions Q4_K_M·103805.0 t/s	Q4_K_M	0.3 GB0%	103805.0 t/s	262K	S100, Runs great
Tiny NemotronHForCausalLM Ultra4MChatFunctions Q4_K_M·103805.0 t/s	Q4_K_M	0.3 GB0%	103805.0 t/s	262K	S100, Runs great

Rent NVIDIA RTX PRO 6000 Blackwell Server Edition in the cloud

Hourly rate on demand for one RTX PRO 6000 Blackwell Server Edition.

Vast.aiMarketplaceLowest price
from$1.55/hr
Deploy
RunPod$5+ bonus credit
from$1.69/hr
Deploy

Cost per million tokens

Output-token cost on an RTX PRO 6000 Blackwell Server Edition rented at $1.55/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	235 tok/s	$1.83$0.0090 input
Gemma 4 26B A4B IT	Q4_K_M	233 tok/s	$1.85$0.017 input
Qwen3.8 27B	Q4_K_M	60 tok/s	$7.22$0.11 input
Muse Glimmer 30B	Q4_K_M	57 tok/s	$7.60$0.11 input
Gemma 4 31B IT	Q4_K_M	51 tok/s	$8.45$0.12 input

RTX PRO 6000 Blackwell Server Edition specs, power and PSU

Specs

Architecture: Blackwell
VRAM: 96 GB GDDR7
Memory bandwidth: 1597.0 GB/s
FP16 (dense): 500.00 TFLOPS
CUDA cores: 24,064
Tensor cores: 752
Compute capability: 12.0
TDP: 600 W
Released: 2025-05-01

RTX PRO 6000 Blackwell Server Edition FAQ

What is the largest model the RTX PRO 6000 Blackwell Server 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 13.4 tok/s.

Can the RTX PRO 6000 Blackwell Server 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 Server Edition give?

About 59.6 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 Server 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 13 coding models that fit, runs at about 60 tok/s.

Best coding LLMs 48 GB VRAM GPUs with 96 GB or more