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 3090 Ti / reasoning

What can NVIDIA GeForce RTX 3090 Ti run for reasoning?

Build: NVIDIA GeForce RTX 3090 Ti + — + 32 GB RAM (windows)

Memory: 24 GB VRAM + 32 GB system RAM
Runner: llama.cpp / Ollama (CUDA)
AnyChatCodingAgentsReasoningVisionLong contextCreative

Runs comfortably
48 models

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

#1Llama 3.1 Nemotron Nano 8B
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 19.1 GBHeadroom: 4.9 GB
128
tok/s
E
Weights
4.83 GB
KV cache
4.00 GB
Activations
8.43 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#2DeepSeek R1 Distill Llama 8B
8B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 19.1 GBHeadroom: 4.9 GB
128
tok/s
E
Weights
4.83 GB
KV cache
4.00 GB
Activations
8.43 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#3Phi-4 Reasoning 14B
14B
phi
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 14.5 GBHeadroom: 9.5 GB
ollama run phi4-reasoning:14b
73
tok/s
E
Weights
8.45 GB
KV cache
1.75 GB
Activations
2.47 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#4DeepSeek R1 Distill Qwen 14B
14B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 14.5 GBHeadroom: 9.5 GB
ollama run deepseek-r1:14b
73
tok/s
E
Weights
8.45 GB
KV cache
1.75 GB
Activations
2.47 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#5DeepSeek V3 Lite (16B MoE)
16B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 16.0 GBHeadroom: 8.0 GB
426
tok/s
E
Weights
9.66 GB
KV cache
2.00 GB
Activations
2.53 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#6Phi-4 14B
14B
phi
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 14.5 GBHeadroom: 9.5 GB
ollama run phi4:14b
73
tok/s
E
Weights
8.45 GB
KV cache
1.75 GB
Activations
2.47 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#7InternLM 2.5 7B Chat
7B
internlm
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 17.9 GBHeadroom: 6.1 GB
146
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 →
#8Qwen 3 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 17.9 GBHeadroom: 6.1 GB
146
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 →
#9Qwen 2.5 Math 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 12.1 GBHeadroom: 11.9 GB
146
tok/s
E
Weights
4.23 GB
KV cache
1.75 GB
Activations
4.31 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#10Granite 3 MoE (3B active)
16B
granite
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 16.0 GBHeadroom: 8.0 GB
341
tok/s
E
Weights
9.66 GB
KV cache
2.00 GB
Activations
2.53 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#11Qwen 3 14B
14B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 14.5 GBHeadroom: 9.5 GB
ollama run qwen3:14b
73
tok/s
E
Weights
8.45 GB
KV cache
1.75 GB
Activations
2.47 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#12Qwen 2.5 14B Instruct
14B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 14.5 GBHeadroom: 9.5 GB
ollama run qwen2.5:14b
73
tok/s
E
Weights
8.45 GB
KV cache
1.75 GB
Activations
2.47 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →

Runs with tradeoffs
49 models

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

DeepSeek R1 Distill Qwen 7B
7B
deepseek
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 21.3 GBHeadroom: 2.7 GB
  • • Tight VRAM fit — only 2.7 GB headroom left for context growth
ollama run deepseek-r1:7b
83
tok/s
E
Weights
7.44 GB
KV cache
3.50 GB
Activations
8.56 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
DeepSeek R1 Distill Mistral 24B
24B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 22.1 GBHeadroom: 1.9 GB
  • • Tight VRAM fit — only 1.9 GB headroom left for context growth
43
tok/s
E
Weights
14.49 GB
KV cache
3.00 GB
Activations
2.77 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
DeepSeek R1 Distill Qwen 32B
32B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 28.1 GBHeadroom: 15.1 GB
  • • Partial CPU offload: ~15% of layers run on CPU
ollama run deepseek-r1:32b
32
tok/s
E
Weights
19.32 GB
KV cache
4.00 GB
Activations
3.01 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
QwQ 32B Preview
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 28.1 GBHeadroom: 15.1 GB
  • • Partial CPU offload: ~15% of layers run on CPU
ollama run qwq:32b
32
tok/s
E
Weights
19.32 GB
KV cache
4.00 GB
Activations
3.01 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
DeepSeek R1 Distill Qwen 3 32B
32B
deepseek
Commercial OK
Quant: AWQ-INT4Context: 2,048VRAM: 41.4 GBHeadroom: 1.8 GB
  • • Partial CPU offload: ~42% of layers run on CPU
19
tok/s
E
Weights
32.00 GB
KV cache
4.00 GB
Activations
3.65 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
Magistral 32B
32B
mistral
Quant: AWQ-INT4Context: 2,048VRAM: 41.4 GBHeadroom: 1.8 GB
  • • Partial CPU offload: ~42% of layers run on CPU
19
tok/s
E
Weights
32.00 GB
KV cache
4.00 GB
Activations
3.65 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
Qwen 3 Coder 32B
32B
qwen
Commercial OK
Quant: AWQ-INT4Context: 2,048VRAM: 41.4 GBHeadroom: 1.8 GB
  • • Partial CPU offload: ~42% of layers run on CPU
19
tok/s
E
Weights
32.00 GB
KV cache
4.00 GB
Activations
3.65 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
Nemotron 3 Nano (30B-A3B)
30B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 26.6 GBHeadroom: 16.6 GB
  • • Partial CPU offload: ~10% of layers run on CPU
ollama run nemotron3:nano
34
tok/s
E
Weights
18.11 GB
KV cache
3.75 GB
Activations
2.95 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: 36 new comfortable, 61 new tradeoff

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

Upgrade to NVIDIA GeForce RTX 5090

~$2499

32 GB VRAM (vs your 24 GB) plus a bandwidth jump from ~? GB/s to ~1792 GB/s.

Unlocks: 64 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 3090 Ti

~$1199

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: 76 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 (24 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 (24 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 (24 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 (24 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 (24 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.