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 3060 12GB / coding

What can NVIDIA GeForce RTX 3060 12GB run for coding?

Build: NVIDIA GeForce RTX 3060 12GB + — + 32 GB RAM (windows)

Memory: 12 GB VRAM + 32 GB system RAM
Runner: llama.cpp / Ollama (CUDA)
AnyChatCodingAgentsReasoningVisionLong contextCreative

Runs comfortably
30 models

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

#1StarCoder 2 3B
3B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 5.2 GBHeadroom: 6.8 GBTTFT: noticeable
129
tok/s
Estimated
Weights
1.81 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~605 ms (noticeable)
Model details →
#2Qwen 2.5 Coder 3B
3B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 5.2 GBHeadroom: 6.8 GBTTFT: noticeable
129
tok/s
Estimated
Weights
1.81 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~605 ms (noticeable)
Model details →
#3ColPali v1.3
3B
gemma
Commercial OK
Quant: Q4_K_MContext: 0VRAM: 3.7 GBHeadroom: 8.3 GBTTFT: noticeable
129
tok/s
Estimated
Weights
1.81 GB
KV cache
0.00 GB
Activations
0.09 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~605 ms (noticeable)
Model details →
#4Orpheus 3B 0.1 FT
3B
other
Commercial OK
Quant: Q4_K_MContext: 0VRAM: 3.7 GBHeadroom: 8.3 GBTTFT: noticeable
129
tok/s
Estimated
Weights
1.81 GB
KV cache
0.00 GB
Activations
0.09 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~605 ms (noticeable)
Model details →
#5Falcon 3 3B Instruct
3B
falcon
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 5.2 GBHeadroom: 6.8 GBTTFT: noticeable
129
tok/s
Estimated
Weights
1.81 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~605 ms (noticeable)
Model details →
#6OpenELM 3B Instruct
3B
other
Quant: Q4_K_MContext: 2,048VRAM: 4.1 GBHeadroom: 7.9 GBTTFT: noticeable
129
tok/s
Estimated
Weights
1.81 GB
KV cache
0.38 GB
Activations
0.09 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~605 ms (noticeable)
Model details →
#7Hermes 3 Llama 3.2 3B
3B
hermes
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 5.2 GBHeadroom: 6.8 GBTTFT: noticeable
129
tok/s
Estimated
Weights
1.81 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~605 ms (noticeable)
Model details →
#8Ministral 3B Instruct
3B
mistral
Quant: Q4_K_MContext: 8,192VRAM: 5.2 GBHeadroom: 6.8 GBTTFT: noticeable
129
tok/s
Estimated
Weights
1.81 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~605 ms (noticeable)
Model details →
#9Dolphin 3.0 Llama 3.2 3B
3B
dolphin
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 5.2 GBHeadroom: 6.8 GBTTFT: noticeable
129
tok/s
Estimated
Weights
1.81 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~605 ms (noticeable)
Model details →
#10SmolLM 3 3B
3B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 5.2 GBHeadroom: 6.8 GBTTFT: noticeable
129
tok/s
Estimated
Weights
1.81 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~605 ms (noticeable)
Model details →
#11Qwen 2.5-VL 3B
3B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 5.2 GBHeadroom: 6.8 GBTTFT: noticeable
129
tok/s
Estimated
Weights
1.81 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~605 ms (noticeable)
Model details →
#12Qwen 2.5 3B Instruct
3B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 5.2 GBHeadroom: 6.8 GBTTFT: noticeable
129
tok/s
Estimated
Weights
1.81 GB
KV cache
1.50 GB
Activations
0.10 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~605 ms (noticeable)
Model details →

Runs with tradeoffs
146 models

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

CodeGemma 7B
7B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 2.3 GBTTFT: noticeable
  • • Tight VRAM fit — only 2.3 GB headroom left for context growth
ollama run codegemma:7b
55
tok/s
Estimated
Weights
4.23 GB
KV cache
3.50 GB
Activations
0.22 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~1411 ms (noticeable)
Model details →
DeepSeek Coder V2 Lite (16B)
16B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 20.0 GBHeadroom: 11.2 GBTTFT: slow
  • • Partial CPU offload: ~40% of layers run on CPU
ollama run deepseek-coder-v2:16b
24
tok/s
Estimated
Weights
9.66 GB
KV cache
8.00 GB
Activations
0.49 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~3225 ms (slow)
Model details →
Codestral 22B
22B
mistral
Quant: Q4_K_MContext: 8,192VRAM: 26.8 GBHeadroom: 4.4 GBTTFT: slow
  • • Partial CPU offload: ~55% of layers run on CPU
ollama run codestral:22b
18
tok/s
Estimated
Weights
13.28 GB
KV cache
11.00 GB
Activations
0.67 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~4435 ms (slow)
Model details →
Qwen 3 8B
8B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.9 GBHeadroom: 1.1 GBTTFT: noticeable
  • • Tight VRAM fit — only 1.1 GB headroom left for context growth
ollama run qwen3:8b
48
tok/s
Estimated
Weights
4.83 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~1613 ms (noticeable)
Model details →
Qwen 2.5 Coder 32B Instruct
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 24.2 GBHeadroom: 7.0 GBTTFT: slow
  • • Partial CPU offload: ~50% of layers run on CPU
ollama run qwen2.5-coder:32b
12
tok/s
Estimated
Weights
19.32 GB
KV cache
2.15 GB
Activations
0.97 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~6450 ms (slow)
Model details →
Qwen 3 30B-A3B
30B
qwen
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 24.6 GBHeadroom: 6.6 GBTTFT: slow
  • • Partial CPU offload: ~51% of layers run on CPU
ollama run qwen3:30b
13
tok/s
Estimated
Weights
18.11 GB
KV cache
3.75 GB
Activations
0.91 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~6047 ms (slow)
Model details →
Gemma 4 31B Dense
31B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 25.3 GBHeadroom: 5.9 GBTTFT: slow
  • • Partial CPU offload: ~53% of layers run on CPU
ollama run gemma4:31b
13
tok/s
Estimated
Weights
18.72 GB
KV cache
3.88 GB
Activations
0.94 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~6249 ms (slow)
Model details →
Qwen 2.5 7B Instruct
7B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 10.1 GBHeadroom: 1.9 GBTTFT: noticeable
  • • Tight VRAM fit — only 1.9 GB headroom left for context growth
ollama run qwen2.5:7b
31
tok/s
Estimated
Weights
7.44 GB
KV cache
0.47 GB
Activations
0.38 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~1411 ms (noticeable)
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: 73 new comfortable, 158 new tradeoff

  • • all-MiniLM-L6-v2
  • • Piper
  • • Whisper Tiny
  • • Whisper Base
Shop this upgrade↗

Upgrade to NVIDIA GeForce RTX 4070 Ti Super

~$829

16 GB VRAM (vs your 12 GB) plus a bandwidth jump from ~360 GB/s to ~672 GB/s.

Unlocks: 142 new comfortable

  • • all-MiniLM-L6-v2
  • • Piper
  • • Whisper Tiny
  • • Whisper Base
Shop this upgrade↗

Add a second NVIDIA GeForce RTX 3060 12GB

~$249

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: 178 new comfortable

  • • all-MiniLM-L6-v2
  • • Piper
  • • Whisper Tiny
  • • Whisper Base
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 (12 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 (12 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 (12 GB) + 60% of system RAM (19 GB) combined.

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

Even with CPU offload, needs more memory than your VRAM (12 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 (12 GB) + 60% of system RAM (19 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.