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 GeForce RTX 3090

What can NVIDIA GeForce RTX 3090 run?

Build: RTX 3090 + Ryzen 9 5950X + 64GB DDR4 (used market)

Memory: 24 GB VRAM + 64 GB system RAM
Runner: llama.cpp / Ollama (CUDA)
AnyChatCodingAgentsReasoningVisionLong contextCreative

Runs comfortably
208 models

Full-VRAM resident, with room for context. No compromises.

#1all-MiniLM-L6-v2
0.022B
other
Commercial OK
Quant: Q4_K_MContext: 256VRAM: 1.8 GBHeadroom: 22.2 GB
45805
tok/s
Estimated
Weights
0.01 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
1.80 GB
Model details →
#2Piper
0.025B
other
Commercial OK
Quant: Q4_K_MContext: 0VRAM: 1.8 GBHeadroom: 22.2 GB
40308
tok/s
Estimated
Weights
0.02 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
1.80 GB
Model details →
#3Whisper Tiny
0.039B
other
Commercial OK
Quant: Q4_K_MContext: 30VRAM: 1.8 GBHeadroom: 22.2 GB
25839
tok/s
Estimated
Weights
0.02 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
1.80 GB
Model details →
#4Whisper Base
0.074B
other
Commercial OK
Quant: Q4_K_MContext: 30VRAM: 1.8 GBHeadroom: 22.2 GB
13618
tok/s
Estimated
Weights
0.04 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
1.80 GB
Model details →
#5Kokoro 82M
0.082B
other
Commercial OK
Quant: Q4_K_MContext: 0VRAM: 1.9 GBHeadroom: 22.1 GB
12289
tok/s
Estimated
Weights
0.05 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
1.80 GB
Model details →
#6all-mpnet-base-v2
0.109B
other
Commercial OK
Quant: Q4_K_MContext: 384VRAM: 1.9 GBHeadroom: 22.1 GB
9245
tok/s
Estimated
Weights
0.07 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
1.80 GB
Model details →
#7paraphrase-multilingual-MiniLM-L12-v2
0.118B
other
Commercial OK
Quant: Q4_K_MContext: 128VRAM: 1.9 GBHeadroom: 22.1 GB
8540
tok/s
Estimated
Weights
0.07 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
1.80 GB
Model details →
#8Nomic Embed Text v1.5
0.137B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 2.0 GBHeadroom: 22.0 GB
7355
tok/s
Estimated
Weights
0.08 GB
KV cache
0.07 GB
Activations
0.01 GB
Runtime
1.80 GB
Model details →
#9SmolLM2 135M Instruct
0.135B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 2.0 GBHeadroom: 22.0 GB
7464
tok/s
Estimated
Weights
0.08 GB
KV cache
0.07 GB
Activations
0.01 GB
Runtime
1.80 GB
Model details →
#10GTE ModernBERT Base
0.149B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 2.0 GBHeadroom: 22.0 GB
6763
tok/s
Estimated
Weights
0.09 GB
KV cache
0.07 GB
Activations
0.01 GB
Runtime
1.80 GB
Model details →
#11Whisper Small
0.244B
other
Commercial OK
Quant: Q4_K_MContext: 30VRAM: 2.0 GBHeadroom: 22.0 GB
4130
tok/s
Estimated
Weights
0.15 GB
KV cache
0.00 GB
Activations
0.01 GB
Runtime
1.80 GB
Model details →
#12Gemma 3 270M
0.27B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 2.1 GBHeadroom: 21.9 GB
3732
tok/s
Estimated
Weights
0.16 GB
KV cache
0.14 GB
Activations
0.02 GB
Runtime
1.80 GB
Model details →

Runs with tradeoffs
65 models

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

Qwen 3 30B-A3B
30B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 50.3 GBHeadroom: 12.1 GB
  • • Partial CPU offload: ~52% of layers run on CPU
  • • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3:30b
1
tok/s
Estimated
Weights
31.88 GB
KV cache
15.00 GB
Activations
1.60 GB
Runtime
1.80 GB
Model details →
Qwen 2.5 Coder 32B Instruct
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 22.6 GBHeadroom: 1.4 GB
  • • Tight VRAM fit — only 1.4 GB headroom left for context growth
ollama run qwen2.5-coder:32b
31
tok/s
Estimated
Weights
19.32 GB
KV cache
0.54 GB
Activations
0.97 GB
Runtime
1.80 GB
Model details →
Llama 3.3 70B Instruct
70B
llama
Commercial OK
Quant: Q5_K_MContext: 8,192VRAM: 55.0 GBHeadroom: 7.4 GB
  • • Partial CPU offload: ~56% of layers run on CPU
  • • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run llama3.3:70b
1
tok/s
Estimated
Weights
48.13 GB
KV cache
2.68 GB
Activations
2.41 GB
Runtime
1.80 GB
Model details →
Qwen 3 32B
32B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 53.5 GBHeadroom: 8.9 GB
  • • Partial CPU offload: ~55% of layers run on CPU
  • • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run qwen3:32b
1
tok/s
Estimated
Weights
34.00 GB
KV cache
16.00 GB
Activations
1.71 GB
Runtime
1.80 GB
Model details →
Gemma 4 31B Dense
31B
gemma
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 51.9 GBHeadroom: 10.5 GB
  • • Partial CPU offload: ~54% of layers run on CPU
  • • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run gemma4:31b
1
tok/s
Estimated
Weights
32.94 GB
KV cache
15.50 GB
Activations
1.66 GB
Runtime
1.80 GB
Model details →
DeepSeek R1 Distill Llama 70B
70B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 54.9 GBHeadroom: 7.5 GB
  • • Partial CPU offload: ~56% of layers run on CPU
  • • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run deepseek-r1:70b
1
tok/s
Estimated
Weights
42.26 GB
KV cache
8.75 GB
Activations
2.12 GB
Runtime
1.80 GB
Model details →
DeepSeek R1 Distill Qwen 32B
32B
deepseek
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 53.5 GBHeadroom: 8.9 GB
  • • Partial CPU offload: ~55% of layers run on CPU
  • • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
ollama run deepseek-r1:32b
1
tok/s
Estimated
Weights
34.00 GB
KV cache
16.00 GB
Activations
1.71 GB
Runtime
1.80 GB
Model details →
Gemma 4 26B MoE
26B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 21.5 GBHeadroom: 2.5 GB
  • • Tight VRAM fit — only 2.5 GB headroom left for context growth
ollama run gemma4:26b-moe
39
tok/s
Estimated
Weights
15.70 GB
KV cache
3.25 GB
Activations
0.79 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: 69 new tradeoff

  • • Qwen 3 30B-A3B
  • • Qwen 2.5 Coder 32B Instruct
  • • Llama 3.3 70B Instruct
  • • Qwen 3 32B
Shop this upgrade↗

Upgrade to NVIDIA RTX PRO 4500 Blackwell

see current pricing

32 GB VRAM (vs your 24 GB) plus a bandwidth jump from ~936 GB/s to ~896 GB/s.

Unlocks: 26 new comfortable

  • • Mistral Nemo 12B Instruct
  • • Gemma 3 12B
  • • Pixtral 12B
  • • Gemma 3 27B
Shop this upgrade↗

Add a second NVIDIA GeForce RTX 3090

~$899

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: 50 new comfortable

  • • Mistral Nemo 12B Instruct
  • • Gemma 3 12B
  • • Pixtral 12B
  • • Gemma 4 26B MoE
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 (38 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 (38 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 (38 GB) combined.

—
DeepSeek R1 (671B reasoning)
671B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 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 (38 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.