RUNLOCALAIv38
→WILL IT RUNBEST GPUCOMPARETROUBLESHOOTSTARTPULSEMODELSHARDWARETOOLSBENCH
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
  • Quick answers
REF
  • All buyer guides
  • 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 GB200 NVL72 / vision

What can NVIDIA GB200 NVL72 run for vision?

Build: NVIDIA GB200 NVL72 + — + 32 GB RAM (windows)

Memory: 13824 GB VRAM + 32 GB system RAM
Runner: llama.cpp / Ollama (CUDA)
AnyChatCodingAgentsReasoningVisionLong contextCreative

Runs comfortably
34 models

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

#1Gemma 4 E2B (Effective 2B)
2B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 13.2 GBHeadroom: 13810.8 GB
ollama run gemma4:e2b
2447
tok/s
E
Weights
2.13 GB
KV cache
1.00 GB
Activations
8.30 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#2Phi-3.5 Vision
4.2B
phi
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 14.8 GBHeadroom: 13809.2 GB
2051
tok/s
E
Weights
2.54 GB
KV cache
2.10 GB
Activations
8.32 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#3Gemma 4 E4B (Effective 4B)
4B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 16.5 GBHeadroom: 13807.5 GB
ollama run gemma4:e4b
1224
tok/s
E
Weights
4.25 GB
KV cache
2.00 GB
Activations
8.40 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#4Gemma 3 4B
4B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 16.5 GBHeadroom: 13807.5 GB
ollama run gemma3:4b
1224
tok/s
E
Weights
4.25 GB
KV cache
2.00 GB
Activations
8.40 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#5Llama 3.2 11B Vision Instruct
11B
llama
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 27.8 GBHeadroom: 13796.2 GB
ollama run llama3.2-vision:11b
445
tok/s
E
Weights
11.69 GB
KV cache
5.50 GB
Activations
8.78 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#6Gemma 3 12B
12B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 29.4 GBHeadroom: 13794.6 GB
ollama run gemma3:12b
408
tok/s
E
Weights
12.75 GB
KV cache
6.00 GB
Activations
8.83 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#7Pixtral 12B
12B
mistral
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 29.4 GBHeadroom: 13794.6 GB
ollama run pixtral:12b
408
tok/s
E
Weights
12.75 GB
KV cache
6.00 GB
Activations
8.83 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#8Gemma 4 26B MoE
26B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 39.5 GBHeadroom: 13784.5 GB
ollama run gemma4:26b-moe
331
tok/s
E
Weights
15.70 GB
KV cache
13.00 GB
Activations
8.98 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#9MedGemma 27B
27B
gemma
Quant: Q4_K_MContext: 8,192VRAM: 40.6 GBHeadroom: 13783.4 GB
319
tok/s
E
Weights
16.30 GB
KV cache
13.50 GB
Activations
9.01 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#10Gemma 3 27B
27B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 53.6 GBHeadroom: 13770.4 GB
ollama run gemma3:27b
181
tok/s
E
Weights
28.69 GB
KV cache
13.50 GB
Activations
9.63 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#11Gemma 4 31B Dense
31B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 60.1 GBHeadroom: 13763.9 GB
ollama run gemma4:31b
158
tok/s
E
Weights
32.94 GB
KV cache
15.50 GB
Activations
9.84 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#12LLaVA 1.6 Mistral 7B
7B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 17.9 GBHeadroom: 13806.1 GB
1230
tok/s
E
Weights
4.23 GB
KV cache
3.50 GB
Activations
8.40 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →

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: 149 new comfortable

  • • Gemma 3 1B
  • • Llama 3.2 1B Instruct
  • • Llama 3.2 3B Instruct
  • • Phi-3.5 Mini Instruct
Shop this upgrade↗

Add a second NVIDIA GB200 NVL72

see current pricing

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: 149 new comfortable

  • • Gemma 3 1B
  • • Llama 3.2 1B Instruct
  • • Llama 3.2 3B Instruct
  • • Phi-3.5 Mini Instruct
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 3 popular models

Need more memory than you have. Shown for orientation.

Qwen 3.6 35B-A3B (MTP)
35B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (13824 GB) + 60% of system RAM (19 GB) combined.

—
Qwen 3.6 27B (MTP)
27B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (13824 GB) + 60% of system RAM (19 GB) combined.

—
Ring-2.6-1T
1000B
other
Commercial OK

Even with CPU offload, needs more memory than your VRAM (13824 GB) + 60% of system RAM (19 GB) combined.

—

How to read these numbers

M
Measured — we ran this exact combo on owner hardware.

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

E
Estimated — pure formula based on VRAM bandwidth and model architecture.

Full methodology →

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