RUNLOCALAIv38
→WILL IT RUNBEST GPUCOMPARETROUBLESHOOTSTARTPULSEMODELSHARDWARETOOLSBENCH
RUNLOCALAI

Operator-grade instrument for local-AI hardware intelligence. Hand-written verdicts. Real benchmarks. Reproducible commands.

OP·Fredoline Eruo
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
  • Will it run?
GUIDES
  • Best GPU
  • Best laptop
  • Best Mac
  • Best used GPU
  • Best budget GPU
  • Best GPU for Ollama
  • Best GPU for SD
  • AI PC build $2K
  • CUDA vs ROCm
  • 16 vs 24 GB
  • Compare hardware
  • Custom compare
REF
  • Systems
  • Ecosystem maps
  • Pillar guides
  • Methodology
  • Glossary
  • Errors KB
  • Troubleshooting
  • Resources
  • Public API
EDITOR
  • About
  • About the author
  • Changelog
  • Latest
  • Updates
  • Submit benchmark
  • Send feedback
  • Trust
  • Editorial policy
  • How we make money
  • 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 →

SYS · ONLINEUPTIME · 100%2026 · operator-owned
RUNLOCALAI · v38
Will it run? / NVIDIA GeForce RTX 4080 Super / vision

What can NVIDIA GeForce RTX 4080 Super run for vision?

Build: NVIDIA GeForce RTX 4080 Super + — + 32 GB RAM (windows)

Memory: 16 GB VRAM + 32 GB system RAM
Runner: llama.cpp / Ollama (CUDA)
AnyChatCodingAgentsReasoningVisionLong contextCreative

Runs comfortably
9 models

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

#1Moondream 2
1.9B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 5.3 GBHeadroom: 10.7 GBTTFT: instant
417
tok/s
E
Weights
1.15 GB
KV cache
0.24 GB
Activations
2.11 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~93 ms (instant)
Model details →Run-on benchmark page →
#2LLaVA 1.6 Mistral 7B
7B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.2 GBHeadroom: 6.8 GBTTFT: fast
113
tok/s
E
Weights
4.23 GB
KV cache
0.88 GB
Activations
2.26 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~343 ms (fast)
Model details →Run-on benchmark page →
#3LLaVA-OneVision 7B
7B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.2 GBHeadroom: 6.8 GBTTFT: fast
113
tok/s
E
Weights
4.23 GB
KV cache
0.88 GB
Activations
2.26 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~343 ms (fast)
Model details →Run-on benchmark page →
#4Qwen 2.5-VL 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.2 GBHeadroom: 6.8 GBTTFT: fast
113
tok/s
E
Weights
4.23 GB
KV cache
0.88 GB
Activations
2.26 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~343 ms (fast)
Model details →Run-on benchmark page →
#5Qwen 2-VL 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.2 GBHeadroom: 6.8 GBTTFT: fast
113
tok/s
E
Weights
4.23 GB
KV cache
0.88 GB
Activations
2.26 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~343 ms (fast)
Model details →Run-on benchmark page →
#6MiniCPM-V 2.6 8B
8B
minicpm
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.9 GBHeadroom: 6.1 GBTTFT: fast
99
tok/s
E
Weights
4.83 GB
KV cache
1.00 GB
Activations
2.29 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~392 ms (fast)
Model details →Run-on benchmark page →
#7MiniCPM-V 3 8B
8B
minicpm
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.9 GBHeadroom: 6.1 GBTTFT: fast
99
tok/s
E
Weights
4.83 GB
KV cache
1.00 GB
Activations
2.29 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~392 ms (fast)
Model details →Run-on benchmark page →
#8PaliGemma 2 3B
3B
gemma
Commercial OK
Quant: BF16Context: 2,048VRAM: 10.5 GBHeadroom: 5.5 GBTTFT: fast
80
tok/s
E
Weights
6.00 GB
KV cache
0.38 GB
Activations
2.35 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~147 ms (fast)
Model details →Run-on benchmark page →
#9Whisper Large v3
1.55B
other
Commercial OK
Quant: FP16Context: 0VRAM: 5.1 GBHeadroom: 10.9 GBTTFT: instant
154
tok/s
E
Weights
3.10 GB
KV cache
0.00 GB
Activations
0.16 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~76 ms (instant)
Model details →Run-on benchmark page →

Runs with tradeoffs
19 models

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

Gemma 4 E4B (Effective 4B)
4B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 14.5 GBHeadroom: 1.5 GBTTFT: fast
  • • Tight VRAM fit — only 1.5 GB headroom left for context growth
ollama run gemma4:e4b
198
tok/s
E
Weights
2.42 GB
KV cache
2.00 GB
Activations
8.31 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~196 ms (fast)
Model details →Run-on benchmark page →
Gemma 3 4B
4B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 14.5 GBHeadroom: 1.5 GBTTFT: fast
  • • Tight VRAM fit — only 1.5 GB headroom left for context growth
ollama run gemma3:4b
198
tok/s
E
Weights
2.42 GB
KV cache
2.00 GB
Activations
8.31 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~196 ms (fast)
Model details →Run-on benchmark page →
Gemma 4 E2B (Effective 2B)
2B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 13.2 GBHeadroom: 2.8 GBTTFT: instant
  • • Tight VRAM fit — only 2.8 GB headroom left for context growth
ollama run gemma4:e2b
225
tok/s
E
Weights
2.13 GB
KV cache
1.00 GB
Activations
8.30 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~98 ms (instant)
Model details →Run-on benchmark page →
Phi-3.5 Vision
4.2B
phi
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 14.8 GBHeadroom: 1.2 GBTTFT: fast
  • • Tight VRAM fit — only 1.2 GB headroom left for context growth
189
tok/s
E
Weights
2.54 GB
KV cache
2.10 GB
Activations
8.32 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~206 ms (fast)
Model details →Run-on benchmark page →
Qwen 2.5-VL 3B
3B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 13.4 GBHeadroom: 2.6 GBTTFT: fast
  • • Tight VRAM fit — only 2.6 GB headroom left for context growth
264
tok/s
E
Weights
1.81 GB
KV cache
1.50 GB
Activations
8.28 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~147 ms (fast)
Model details →Run-on benchmark page →
Janus-Pro 7B
7B
janus
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 12.1 GBHeadroom: 3.9 GBTTFT: fast
  • • Tight VRAM fit — only 3.9 GB headroom left for context growth
113
tok/s
E
Weights
4.23 GB
KV cache
1.75 GB
Activations
4.31 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~343 ms (fast)
Model details →Run-on benchmark page →
Molmo 7B-D
8B
other
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 13.0 GBHeadroom: 3.0 GBTTFT: fast
  • • Tight VRAM fit — only 3.0 GB headroom left for context growth
99
tok/s
E
Weights
4.83 GB
KV cache
2.00 GB
Activations
4.34 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~392 ms (fast)
Model details →Run-on benchmark page →
Llama 3.2 11B Vision Instruct
11B
llama
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 12.2 GBHeadroom: 3.8 GBTTFT: noticeable
  • • Tight VRAM fit — only 3.8 GB headroom left for context growth
ollama run llama3.2-vision:11b
72
tok/s
E
Weights
6.64 GB
KV cache
1.38 GB
Activations
2.38 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~539 ms (noticeable)
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: 44 new comfortable, 82 new tradeoff

  • • Gemma 3 1B
  • • Llama 3.2 1B Instruct
  • • DeepSeek R1 Distill Qwen 7B
  • • Llama 3.1 8B Instruct
Shop this upgrade↗

Upgrade to NVIDIA GeForce RTX 3090 Ti

~$1199

24 GB VRAM (vs your 16 GB) plus a bandwidth jump from ~736 GB/s to ~? GB/s.

Unlocks: 75 new comfortable

  • • Gemma 3 1B
  • • Llama 3.2 1B Instruct
  • • Gemma 4 E2B (Effective 2B)
  • • Llama 3.2 3B Instruct
Shop this upgrade↗

Add a second NVIDIA GeForce RTX 4080 Super

~$1099

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: 100 new comfortable

  • • Gemma 3 1B
  • • Llama 3.2 1B Instruct
  • • Gemma 4 E2B (Effective 2B)
  • • Llama 3.2 3B 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 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 (16 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 (16 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 (16 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 (16 GB) + 60% of system RAM (19 GB) combined.

—
Llama 4 Scout
109B
llama
Commercial OK

Even with CPU offload, needs more memory than your VRAM (16 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.