RUNLOCALAIv38
->Will it run?Best GPUCompareTroubleshootStartLearnPulseModelsHardwareToolsBench
Run check
RUNLOCALAI

Independently operated catalog for local-AI hardware and software. Hand-written verdicts. Source-cited claims. Reproducible commands when we have them.

OP·Fredoline Eruo
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
TOOLS
  • Will it run?
  • Compare hardware
  • Cost vs cloud
  • Choose my GPU
  • Prompting kits
  • Quick answers
REF
  • All buyer guides
  • Learn local AI
  • Methodology
  • Glossary
  • Errors KB
  • Trust
EDITOR
  • About
  • Author
  • How we make money
  • Editorial policy
  • Contact
LEGAL
  • Privacy
  • Terms
  • Sitemap
MAIL · MONTHLY DIGEST
Get monthly local AI changes
Monthly recap. No spam.
DISCLOSURE

Some links on this site are affiliate links (Amazon Associates and other first-class retailers). When you buy through them, we earn a small commission at no extra cost to you. Affiliate links do not influence our verdicts — there are cards we rate highly that we don't have affiliate relationships with, and cards that sell well that we refuse to recommend. Read more →

© 2026 runlocalai.coIndependently operated
RUNLOCALAI · v38
Will it run? / NVIDIA RTX PRO 6000 Blackwell / agents

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)
AnyChatCodingAgentsReasoningVisionLong contextCreative

Runs comfortably
185 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
Model details →
#2Dolphin 3.0 Mistral 24B
24B
dolphin
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 29.0 GBHeadroom: 67.0 GB
ollama run dolphin-mistral:24b
80
tok/s
Estimated
Weights
14.49 GB
KV cache
12.00 GB
Activations
0.73 GB
Runtime
1.80 GB
Model details →
#3Qwen 2.5 14B Instruct
14B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 24.4 GBHeadroom: 71.6 GB
ollama run qwen2.5:14b
78
tok/s
Estimated
Weights
14.88 GB
KV cache
7.00 GB
Activations
0.75 GB
Runtime
1.80 GB
Model details →
#4Qwen 2.5 7B Instruct
7B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 10.1 GBHeadroom: 85.9 GB
ollama run qwen2.5:7b
157
tok/s
Estimated
Weights
7.44 GB
KV cache
0.47 GB
Activations
0.38 GB
Runtime
1.80 GB
Model details →
#5Qwen 3 30B-A3B
30B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 50.3 GBHeadroom: 45.7 GB
ollama run qwen3:30b
37
tok/s
Estimated
Weights
31.88 GB
KV cache
15.00 GB
Activations
1.60 GB
Runtime
1.80 GB
Model details →
#6Qwen 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
Model details →
#7Qwen 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
Model details →
#8Qwen 2.5 32B Instruct
32B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 53.5 GBHeadroom: 42.5 GB
ollama run qwen2.5:32b
34
tok/s
Estimated
Weights
34.00 GB
KV cache
16.00 GB
Activations
1.71 GB
Runtime
1.80 GB
Model details →
#9Nemotron 3 Nano (30B-A3B)
30B
other
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 50.3 GBHeadroom: 45.7 GB
ollama run nemotron3:nano
37
tok/s
Estimated
Weights
31.88 GB
KV cache
15.00 GB
Activations
1.60 GB
Runtime
1.80 GB
Model details →
#10Gemma 4 26B MoE
26B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 31.3 GBHeadroom: 64.7 GB
ollama run gemma4:26b-moe
74
tok/s
Estimated
Weights
15.70 GB
KV cache
13.00 GB
Activations
0.79 GB
Runtime
1.80 GB
Model details →
#11Mixtral 8x7B Instruct
47B
mixtral
Commercial OK
Quant: Q5_K_MContext: 8,192VRAM: 59.2 GBHeadroom: 36.8 GB
ollama run mixtral:8x7b
36
tok/s
Estimated
Weights
32.31 GB
KV cache
23.50 GB
Activations
1.62 GB
Runtime
1.80 GB
Model details →
#12Llama 3.1 Nemotron Nano 8B
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.9 GBHeadroom: 85.1 GB
241
tok/s
Estimated
Weights
4.83 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
1.80 GB
Model details →

Runs with tradeoffs
6 models

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

Nemotron 3 Super (120B-A12B)
120B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 92.9 GBHeadroom: 3.1 GB
  • • Tight VRAM fit — only 3.1 GB headroom left for context growth
ollama run nemotron3:super
16
tok/s
Estimated
Weights
72.45 GB
KV cache
15.00 GB
Activations
3.62 GB
Runtime
1.80 GB
Model details →
Mixtral 8x22B Instruct
141B
mixtral
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 108.8 GBHeadroom: 6.4 GB
  • • Partial CPU offload: ~12% of layers run on CPU
ollama run mixtral:8x22b
14
tok/s
Estimated
Weights
85.13 GB
KV cache
17.63 GB
Activations
4.26 GB
Runtime
1.80 GB
Model details →
DBRX Base
132B
dbrx
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 102.0 GBHeadroom: 13.2 GB
  • • Partial CPU offload: ~6% of layers run on CPU
54
tok/s
Estimated
Weights
79.69 GB
KV cache
16.50 GB
Activations
3.99 GB
Runtime
1.80 GB
Model details →
Mistral Large 2 (123B)
123B
mistral
Quant: Q4_K_MContext: 2,048VRAM: 95.2 GBHeadroom: 0.8 GB
  • • Tight VRAM fit — only 0.8 GB headroom left for context growth
ollama run mistral-large:123b
16
tok/s
Estimated
Weights
74.26 GB
KV cache
15.38 GB
Activations
3.72 GB
Runtime
1.80 GB
Model details →
WizardLM-2 8x22B
141B
wizard
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 108.8 GBHeadroom: 6.4 GB
  • • Partial CPU offload: ~12% of layers run on CPU
14
tok/s
Estimated
Weights
85.13 GB
KV cache
17.63 GB
Activations
4.26 GB
Runtime
1.80 GB
Model details →
Llama 3.2 90B Vision
90B
llama
Commercial OK
Quant: AWQ-INT4Context: 2,048VRAM: 107.6 GBHeadroom: 7.6 GB
  • • Partial CPU offload: ~11% of layers run on CPU
13
tok/s
Estimated
Weights
90.00 GB
KV cache
11.25 GB
Activations
4.50 GB
Runtime
1.80 GB
Model details →

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: 98 new comfortable, 7 new tradeoff

  • • all-MiniLM-L6-v2
  • • Piper
  • • Whisper Tiny
  • • Whisper Base
Shop this upgrade↗

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: 104 new comfortable

  • • all-MiniLM-L6-v2
  • • Piper
  • • Whisper Tiny
  • • Whisper Base
Shop this upgrade↗

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: 112 new comfortable

  • • all-MiniLM-L6-v2
  • • Piper
  • • Whisper Tiny
  • • Whisper Base
Shop this upgrade↗

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.