What can NVIDIA RTX PRO 6000 Blackwell run for agents?

Build: NVIDIA RTX PRO 6000 Blackwell + — + 32 GB RAM (windows)

Memory: 96 GB VRAM + 32 GB system RAM
Runner: llama.cpp / Ollama (CUDA)

Runs comfortably
200 models

Ranked by fit for agents use case + predicted speed. Click a row for VRAM breakdown.

#1Hermes 3 Llama 3.1 8B
8B
hermes
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 14.7 GBHeadroom: 81.3 GB
ollama run hermes3:8b
137
tok/s
Estimated
Weights
8.50 GB
KV cache
4.00 GB
Activations
0.43 GB
Runtime
1.80 GB
#2Dolphin 3.0 Mistral 24B
24B
dolphin
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 28.5 GBHeadroom: 67.5 GB
ollama run dolphin-mistral:24b
80
tok/s
Estimated
Weights
14.00 GB
KV cache
12.00 GB
Activations
0.71 GB
Runtime
1.80 GB
#3Qwen 2.5 14B Instruct
14B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 25.3 GBHeadroom: 70.7 GB
ollama run qwen2.5:14b
78
tok/s
Estimated
Weights
15.70 GB
KV cache
7.00 GB
Activations
0.79 GB
Runtime
1.80 GB
#4Qwen3 Coder 30B-A3B
30B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 36.8 GBHeadroom: 59.2 GB
ollama run qwen3-coder:30b
64
tok/s
Estimated
Weights
19.00 GB
KV cache
15.00 GB
Activations
0.96 GB
Runtime
1.80 GB
#5Qwen 2.5 7B Instruct
7B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 10.8 GBHeadroom: 85.2 GB
ollama run qwen2.5:7b
157
tok/s
Estimated
Weights
8.10 GB
KV cache
0.47 GB
Activations
0.41 GB
Runtime
1.80 GB
#6North Mini Code 1.0
30B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 36.8 GBHeadroom: 59.2 GB
ollama run north-mini-code-1.0
64
tok/s
Estimated
Weights
19.00 GB
KV cache
15.00 GB
Activations
0.96 GB
Runtime
1.80 GB
#7GLM-4.7-Flash
31B
glm
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 37.3 GBHeadroom: 58.7 GB
ollama run glm-4.7-flash
62
tok/s
Estimated
Weights
19.00 GB
KV cache
15.50 GB
Activations
0.96 GB
Runtime
1.80 GB
#8Laguna XS 2.1
33B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 39.3 GBHeadroom: 56.7 GB
ollama run laguna-xs-2.1
58
tok/s
Estimated
Weights
20.00 GB
KV cache
16.50 GB
Activations
1.01 GB
Runtime
1.80 GB
#9Ornith 1.0 35B
35B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 41.4 GBHeadroom: 54.6 GB
ollama run ornith:35b
55
tok/s
Estimated
Weights
21.00 GB
KV cache
17.50 GB
Activations
1.06 GB
Runtime
1.80 GB
#10Qwen 3 30B-A3B
30B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 50.4 GBHeadroom: 45.6 GB
ollama run qwen3:30b
37
tok/s
Estimated
Weights
32.00 GB
KV cache
15.00 GB
Activations
1.61 GB
Runtime
1.80 GB
#11Qwen 2.5 Coder 32B Instruct
32B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 39.7 GBHeadroom: 56.3 GB
ollama run qwen2.5-coder:32b
34
tok/s
Estimated
Weights
34.00 GB
KV cache
2.15 GB
Activations
1.71 GB
Runtime
1.80 GB
#12Qwen 3 32B
32B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 53.5 GBHeadroom: 42.5 GB
ollama run qwen3:32b
34
tok/s
Estimated
Weights
34.00 GB
KV cache
16.00 GB
Activations
1.71 GB
Runtime
1.80 GB

Runs with tradeoffs
7 models

Tight VRAM, partial CPU offload, or context-limited.

Nemotron 3 Super (120B-A12B)
120B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 92.4 GBHeadroom: 3.6 GB
  • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run nemotron3:super
16
tok/s
Estimated
Weights
72.00 GB
KV cache
15.00 GB
Activations
3.60 GB
Runtime
1.80 GB
Mixtral 8x22B Instruct
141B
mixtral
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 107.6 GBHeadroom: 7.6 GB
  • Partial CPU offload: ~11% of layers run on CPU
ollama run mixtral:8x22b
14
tok/s
Estimated
Weights
84.00 GB
KV cache
17.63 GB
Activations
4.20 GB
Runtime
1.80 GB
GLM-5 Pro
144B
glm
Quant: AWQ-INT4Context: 2,048VRAM: 105.9 GBHeadroom: 9.3 GB
  • Partial CPU offload: ~9% of layers run on CPU
73
tok/s
Estimated
Weights
82.00 GB
KV cache
18.00 GB
Activations
4.10 GB
Runtime
1.80 GB
DBRX Base
132B
dbrx
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 97.1 GBHeadroom: 18.1 GB
  • Partial CPU offload: ~1% of layers run on CPU
54
tok/s
Estimated
Weights
75.00 GB
KV cache
16.50 GB
Activations
3.75 GB
Runtime
1.80 GB
DBRX Instruct
132B
dbrx
Commercial OK
Quant: AWQ-INT4Context: 2,048VRAM: 97.1 GBHeadroom: 18.1 GB
  • Partial CPU offload: ~1% of layers run on CPU
32
tok/s
Estimated
Weights
75.00 GB
KV cache
16.50 GB
Activations
3.75 GB
Runtime
1.80 GB
Quant: Q4_K_MContext: 2,048VRAM: 93.8 GBHeadroom: 2.2 GB
  • Tight VRAM fit — only 2.2 GB headroom left for context growth
ollama run mistral-large:123b
16
tok/s
Estimated
Weights
73.00 GB
KV cache
15.38 GB
Activations
3.65 GB
Runtime
1.80 GB
WizardLM-2 8x22B
141B
wizard
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 107.6 GBHeadroom: 7.6 GB
  • Partial CPU offload: ~11% of layers run on CPU
14
tok/s
Estimated
Weights
84.00 GB
KV cache
17.63 GB
Activations
4.20 GB
Runtime
1.80 GB

What if you upgraded?

Hypothetical scenarios. We re-ran the compatibility engine for each.

+32 GB system RAM

~$80–150

Doubles your CPU-offload working set. Helps when models don't quite fit in VRAM.

Unlocks: 64 new comfortable, 7 new tradeoff

  • Qwen 3 0.6B
  • Llama 3.2 3B Instruct
  • Qwen 3 1.7B
  • Gemma 3 270M

Upgrade to NVIDIA H200 NVL (PCIe)

~$32000

141 GB VRAM (vs your 96 GB) plus a bandwidth jump from ~1792 GB/s to ~4800 GB/s.

Unlocks: 69 new comfortable

  • Qwen 3 0.6B
  • Llama 3.2 3B Instruct
  • Qwen 3 1.7B
  • Gemma 3 270M

Add a second NVIDIA RTX PRO 6000 Blackwell

~$8999

Tensor parallelism splits the model across both cards, effectively doubling VRAM. Bandwidth doesn't double — runs ~1.5× the single-card speed in practice.

Unlocks: 78 new comfortable

  • Qwen 3 235B-A22B
  • Qwen 3 0.6B
  • GLM-5
  • Llama 3.2 3B Instruct

Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.

Won't run
top 5 popular models

Need more memory than you have. Shown for orientation.

DeepSeek V4 Pro (1.6T MoE)
1600B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (19 GB) combined.

Qwen 3.5 235B-A17B (MoE)
397B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (19 GB) combined.

Qwen 3 235B-A22B
235B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (19 GB) combined.

DeepSeek R1 (671B reasoning)
671B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (19 GB) combined.

DeepSeek V4 Flash (284B MoE)
284B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (96 GB) + 60% of system RAM (19 GB) combined.

How to read these numbers

Measured here
Measured here - RunLocalAI ran this exact combo on owner hardware with public evidence.

Source-backed
Source-backed / community - a reproduced public source supports the speed, but it is not labeled as owner-measured.

Extrapolated
Extrapolated - predicted from a measured benchmark on similar-bandwidth hardware.

Estimated
Estimated - formula based on VRAM bandwidth and model architecture; not a benchmark row.

RunLocalAI Will-It-Run Framework →

Want a specific benchmark we don't have? Email Contact support and we'll prioritize it.