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 4070 Ti Super / agents

What can NVIDIA GeForce RTX 4070 Ti Super run for agents?

Build: NVIDIA GeForce RTX 4070 Ti Super + — + 32 GB RAM (windows)

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

Runs comfortably
36 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: Q4_K_MContext: 2,048VRAM: 9.9 GBHeadroom: 6.1 GB
ollama run hermes3:8b
94
tok/s
E
Weights
4.83 GB
KV cache
1.00 GB
Activations
2.29 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#2Mistral 7B Instruct v0.3
7B
mistral
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.2 GBHeadroom: 6.8 GB
ollama run mistral:7b
108
tok/s
E
Weights
4.23 GB
KV cache
0.88 GB
Activations
2.26 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#3Llama 3.1 8B Instruct
8B
llama
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.2 GBHeadroom: 6.8 GB
ollama run llama3.1:8b
94
tok/s
E
Weights
4.83 GB
KV cache
0.27 GB
Activations
2.29 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#4Llama 3.1 Nemotron Nano 8B
8B
llama
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.9 GBHeadroom: 6.1 GB
94
tok/s
E
Weights
4.83 GB
KV cache
1.00 GB
Activations
2.29 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#5CodeQwen 1.5 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.2 GBHeadroom: 6.8 GB
108
tok/s
E
Weights
4.23 GB
KV cache
0.88 GB
Activations
2.26 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#6Qwen 2.5 Coder 7B Instruct
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.2 GBHeadroom: 6.8 GB
ollama run qwen2.5-coder:7b
108
tok/s
E
Weights
4.23 GB
KV cache
0.88 GB
Activations
2.26 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#7Qwen 2.5-VL 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.2 GBHeadroom: 6.8 GB
108
tok/s
E
Weights
4.23 GB
KV cache
0.88 GB
Activations
2.26 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#8Qwen 3 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.2 GBHeadroom: 6.8 GB
108
tok/s
E
Weights
4.23 GB
KV cache
0.88 GB
Activations
2.26 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#9Qwen 2-VL 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.2 GBHeadroom: 6.8 GB
108
tok/s
E
Weights
4.23 GB
KV cache
0.88 GB
Activations
2.26 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#10Qwen 3 8B
8B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.9 GBHeadroom: 6.1 GB
ollama run qwen3:8b
94
tok/s
E
Weights
4.83 GB
KV cache
1.00 GB
Activations
2.29 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#11DeepSeek R1 Distill Qwen 7B
7B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.2 GBHeadroom: 6.8 GB
ollama run deepseek-r1:7b
108
tok/s
E
Weights
4.23 GB
KV cache
0.88 GB
Activations
2.26 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
#12CodeGemma 7B
7B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 9.2 GBHeadroom: 6.8 GB
ollama run codegemma:7b
108
tok/s
E
Weights
4.23 GB
KV cache
0.88 GB
Activations
2.26 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →

Runs with tradeoffs
54 models

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

Qwen 2.5 14B Instruct
14B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 14.5 GBHeadroom: 1.5 GB
  • • Tight VRAM fit — only 1.5 GB headroom left for context growth
ollama run qwen2.5:14b
54
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 →
Qwen 2.5 7B Instruct
7B
qwen
Commercial OK
Quant: Q5_K_MContext: 8,192VRAM: 15.5 GBHeadroom: 0.5 GB
  • • Tight VRAM fit — only 0.5 GB headroom left for context growth
ollama run qwen2.5:7b
95
tok/s
E
Weights
4.81 GB
KV cache
0.47 GB
Activations
8.43 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
Dolphin 3.0 Mistral 24B
24B
dolphin
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 22.1 GBHeadroom: 13.1 GB
  • • Partial CPU offload: ~27% of layers run on CPU
ollama run dolphin-mistral:24b
31
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 →
Qwen 3 30B-A3B
30B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 26.6 GBHeadroom: 8.6 GB
  • • Partial CPU offload: ~40% of layers run on CPU
ollama run qwen3:30b
25
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 →
Qwen 2.5 Coder 32B Instruct
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 32.4 GBHeadroom: 2.8 GB
  • • Partial CPU offload: ~51% of layers run on CPU
ollama run qwen2.5-coder:32b
24
tok/s
E
Weights
19.32 GB
KV cache
2.15 GB
Activations
9.16 GB
Runtime
1.80 GB
Model details →Run-on benchmark page →
Qwen 3 32B
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 28.1 GBHeadroom: 7.1 GB
  • • Partial CPU offload: ~43% of layers run on CPU
ollama run qwen3:32b
24
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 →
Qwen 2.5 32B Instruct
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 28.1 GBHeadroom: 7.1 GB
  • • Partial CPU offload: ~43% of layers run on CPU
ollama run qwen2.5:32b
24
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 →
Nemotron 3 Nano (30B-A3B)
30B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 26.6 GBHeadroom: 8.6 GB
  • • Partial CPU offload: ~40% of layers run on CPU
ollama run nemotron3:nano
25
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: 17 new comfortable, 82 new tradeoff

  • • Gemma 3 1B
  • • Llama 3.2 1B Instruct
  • • Moondream 2
  • • Whisper Large v3 Turbo
Shop this upgrade↗

Upgrade to NVIDIA GeForce RTX 3090 Ti

~$1199

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

Unlocks: 56 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 4070 Ti Super

~$829

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: 73 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.