NVIDIA · Blackwell · 16 GB VRAM tier

Best AI Models for NVIDIA RTX PRO 2000 Blackwell (16 GB)

Runs 14B models well; 27–31B barely fits and is slow (13 tok/s).

16 GB GDDR7288 GB/s70 WBlackwell 2025

Entry 70 W low-profile workstation card; 288 GB/s bandwidth is the limiting factor for inference. NVIDIA published only "Q4 2025" availability, so the release date here is the quarter, not a confirmed retail day.

What LLMs can the RTX PRO 2000 Blackwell run?

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 29.4 t/s	29.4 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 57.4 t/s	57.4 tok/s	Q4_K_M · 3.4 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 66.0 t/s	66.0 tok/s	Q4_K_M · 13.1 GB
4	Phi 4Microsoft Q4_K_M · 12.5 GB · 19.7 t/s	19.7 tok/s	Q4_K_M · 12.5 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 22.7 t/s	22.7 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed	Coding Score	Quant · VRAM
1	GPT OSS 20BOpenAIHow to run → Q4_K_M · 13.1 GB · 66.0 t/s	66.0 tok/s		Q4_K_M · 13.1 GB
2	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 35.3 t/s	35.3 tok/s		Q4_K_M · 7.9 GB
3	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 29.4 t/s	29.4 tok/s	overall	Q4_K_M · 6.6 GB
4	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 22.7 t/s	22.7 tok/s		Q4_K_M · 9.0 GB
5	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 158 t/s	158 tok/s		Q4_K_M · 5.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 29.4 t/s	29.4 tok/s	Q4_K_M · 6.6 GB
2	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 66.0 t/s	66.0 tok/s	Q4_K_M · 13.1 GB
3	Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 33.9 t/s	33.9 tok/s	Q4_K_M · 7.6 GB
4	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 35.3 t/s	35.3 tok/s	Q4_K_M · 7.9 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 22.7 t/s	22.7 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 29.4 t/s	29.4 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 57.4 t/s	57.4 tok/s	Q4_K_M · 3.4 GB
3	Mistral Nemo Instruct 2407Mistral AI Q4_K_M · 11.0 GB · 23.2 t/s	23.2 tok/s	Q4_K_M · 11.0 GB
4	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 35.3 t/s	35.3 tok/s	Q4_K_M · 7.9 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 22.7 t/s	22.7 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed ↓	Quant · VRAM
1	GPT OSS 20BOpenAIHow to run → Q4_K_M · 13.1 GB · 66.0 t/s	66.0 tok/s	Q4_K_M · 13.1 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 57.4 t/s	57.4 tok/s	Q4_K_M · 3.4 GB
3	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 29.4 t/s	29.4 tok/s	Q4_K_M · 6.6 GB
4	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 22.7 t/s	22.7 tok/s	Q4_K_M · 9.0 GB
5	Phi 4Microsoft Q4_K_M · 12.5 GB · 19.7 t/s	19.7 tok/s	Q4_K_M · 12.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 29.4 t/s	29.4 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 57.4 t/s	57.4 tok/s	Q4_K_M · 3.4 GB
3	Gemma 3 12B ITGoogle Q4_K_M · 10.9 GB · 23.3 t/s	23.3 tok/s	Q4_K_M · 10.9 GB
4	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 65.9 t/s	65.9 tok/s	Q4_K_M · 5.0 GB
5	MiMo V2.6 Distill Qwen 9BXiaomi Q4_K_M · 6.5 GB · 30.1 t/s	30.1 tok/s	Q4_K_M · 6.5 GB

See all 307 models on the RTX PRO 2000 Blackwell →Best quant that fits · speeds estimated on this card

About the RTX PRO 2000 Blackwell

The RTX PRO 2000 Blackwell runs 14B models well. Blackwell generation, released 2025.

GenerationBlackwellreleased 2025

RTX PRO 2000 Blackwell strengths and weaknesses

Strengths

Runs 35B MoE models: Qwen3.6 35B A3B at 75.5 tok/s in 15.7 GB
Low power draw: 70 W board power; a 150 W PSU is enough

Weaknesses

70B models don't fit: Llama 3.3 70B Instruct needs 51.3 GB at Q4 vs 16 GB here
Slow on large dense models: Qwen3.8 27B at 12.5 tok/s

RTX PRO 2000 Blackwell tokens per second by model size

Output speed depends on memory bandwidth (288 GB/s). Grey rows need more than 16 GB.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
29.4tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
19.7tok/s
27–31BQwen3.8 27B · Q3_K_L · 15.4 GB tight · Q3_K_L
12.5tok/s
35B MoEQwen3.6 35B A3B · IQ3_S · 15.7 GB tight · IQ3_S
75.5tok/s
70BLlama 3.3 70B Instruct · not at 4-bit
needs 51.3 GB
120B MoEGPT OSS 120B · not at 4-bit
needs 70.8 GB

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

All 1057 models on the RTX PRO 2000 Blackwell

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 2000 Blackwell — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
LFM2.5 350M354MChatFunctions Q4_K_M·322.8 t/s	Q4_K_M	0.8 GB5%	322.8 t/s	128K	S100, Runs great
Veritas 8B Fact Checker Non Thinking 1.08.2BChat Q4_K_M·33.9 t/s	Q4_K_M	7.6 GB48%	33.9 t/s	41K	A73, Runs well
Tiny Random Gemma2ForCausalLM8MChat Q4_K_M·603.9 t/s	Q4_K_M	0.3 GB2%	603.9 t/s	8K	S100, Runs great
Qwen3 Tiny Random10MChatFunctions Q4_K_M·603.9 t/s	Q4_K_M	0.3 GB2%	603.9 t/s	41K	S100, Runs great
Gemma 4 12B Agentic Fable5 Composer2.5 v2 3.5x Tau212.0BChatFunctionsReasoning Q4_K_M·22.7 t/s	Q4_K_M	9.0 GB56%	22.7 t/s	262K	B63, Decent
Qwen3 4B Hindi Instruct v24.0BChat Q4_K_M·64.6 t/s	Q4_K_M	4.2 GB26%	64.6 t/s	262K	A84, Runs well
Ouro Hybrid 1.4B1.5BChat BF16·50.2 t/s	BF16	6.5 GB41%	50.2 t/s	66K	A79, Runs well
Jan V3.5 4B4.4BChatMath Q4_K_M·59.6 t/s	Q4_K_M	4.5 GB28%	59.6 t/s	262K	A84, Runs well
ERNIE 4.5 21B A3B Thinking21.8BChatFunctions Q4_K_M·79.2 t/s	Q4_K_M	14.3 GB90%	79.2 t/s	131K	A73, Runs well
DeepSeek R1 Distill Qwen 1.5B1.8BChatReasoningFunctions Q4_K_M·131.8 t/s	Q4_K_M	1.8 GB11%	131.8 t/s	131K	S95, Runs great
Qwen3.5 9B Uncensored9BChat Q4_K_M·31.5 t/s	Q4_K_M	8.6 GB54%	31.5 t/s	—	A71, Runs well
Clef27.4BVisionFunctions IQ4_XS·12.1 t/s	IQ4_XS	15.9 GB99%	12.1 t/s	262K	D21, Barely runs
Ouro 2.6B Thinking2.7BChatReasoning BF16·29.1 t/s	BF16	12.1 GB76%	29.1 t/s	66K	A70, Runs well
Qwen3.5 9B Claude 4.6 Opus Reasoning Distilled9.7BChatReasoning Q4_K_M·29.4 t/s	Q4_K_M	6.6 GB41%	29.4 t/s	262K	A70, Runs well
Jina Ocr V13.4BVision Q4_K_M·191.3 t/s	Q4_K_M	3.3 GB21%	191.3 t/s	33K	S99, Runs great

RTX PRO 2000 Blackwell specs, power and PSU

Specs

Architecture: Blackwell
VRAM: 16 GB GDDR7
Memory bandwidth: 288.0 GB/s
CUDA cores: 4,352
Compute capability: 12.0
TDP: 70 W
Released: 2025-10-01

RTX PRO 2000 Blackwell FAQ

What is the largest model the RTX PRO 2000 Blackwell can run?

Gemma 4 26B A4B IT (25.8B) is the largest at 4-bit or better: at Q4_K_S it uses 15.5 GB of 16 GB, and runs at about 64.8 tok/s. At 3-bit, a bigger model fits too: Gemma 2 27B IT (27.2B) at IQ3_M, 15.0 GB.

Can the RTX PRO 2000 Blackwell run Qwen3.5 9B?

Yes. Qwen3.5 9B fits at Q4_K_M, using 6.6 GB of 16 GB, and it is the best model that runs well on this card.

Can the RTX PRO 2000 Blackwell run 70B models?

No. Llama 3.3 70B Instruct needs 51.3 GB at Q4, more than the 16 GB on this card.

How many tokens per second does the RTX PRO 2000 Blackwell give?

About 29.4 tok/s on Qwen3.5 9B at Q4_K_M.

What power supply does the RTX PRO 2000 Blackwell need?

Plan a 150 W PSU (2× the 70 W TDP).

Is 16 GB enough for coding and agents?

Yes for coding: GPT OSS 20B, the best of the 2 coding models that fit, runs at about 66 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Best coding LLMs 16 GB VRAM 24 GB VRAM GPUs with 16 GB or more RTX 5090 RTX 3090 Ti