What can NVIDIA GeForce RTX 3090 run for coding?

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

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

Runs comfortably
143 models

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

#1CodeGemma 7B
7B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 14.3 GB
ollama run codegemma:7b
144
tok/s
Estimated
Weights
4.20 GB
KV cache
3.50 GB
Activations
0.22 GB
Runtime
1.80 GB
#2DeepSeek Coder V2 Lite (16B)
16B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 19.8 GBHeadroom: 4.2 GB
ollama run deepseek-coder-v2:16b
63
tok/s
Estimated
Weights
9.50 GB
KV cache
8.00 GB
Activations
0.48 GB
Runtime
1.80 GB
#3Codestral 22B
22B
mistral
Quant: Q4_K_MContext: 2,048VRAM: 18.2 GBHeadroom: 5.8 GB
ollama run codestral:22b
46
tok/s
Estimated
Weights
13.00 GB
KV cache
2.75 GB
Activations
0.65 GB
Runtime
1.80 GB
#4Qwen 3 14B
14B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 17.6 GBHeadroom: 6.4 GB
ollama run qwen3:14b
72
tok/s
Estimated
Weights
8.40 GB
KV cache
7.00 GB
Activations
0.43 GB
Runtime
1.80 GB
#5Qwen 2.5 14B Instruct
14B
qwen
Commercial OK
Quant: Q5_K_MContext: 8,192VRAM: 19.8 GBHeadroom: 4.2 GB
ollama run qwen2.5:14b
63
tok/s
Estimated
Weights
10.50 GB
KV cache
7.00 GB
Activations
0.53 GB
Runtime
1.80 GB
#6Qwen 2.5 7B Instruct
7B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 10.8 GBHeadroom: 13.2 GB
ollama run qwen2.5:7b
82
tok/s
Estimated
Weights
8.10 GB
KV cache
0.47 GB
Activations
0.41 GB
Runtime
1.80 GB
#7Qwen 3 8B
8B
qwen
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 14.4 GBHeadroom: 9.6 GB
ollama run qwen3:8b
72
tok/s
Estimated
Weights
8.20 GB
KV cache
4.00 GB
Activations
0.42 GB
Runtime
1.80 GB
#8Mistral Small 3 24B
24B
mistral
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 19.5 GBHeadroom: 4.5 GB
ollama run mistral-small:24b
42
tok/s
Estimated
Weights
14.00 GB
KV cache
3.00 GB
Activations
0.70 GB
Runtime
1.80 GB
#9Llama 3.1 8B Instruct
8B
llama
Commercial OK
Quant: FP16Context: 8,192VRAM: 19.8 GBHeadroom: 4.2 GB
ollama run llama3.1:8b
38
tok/s
Estimated
Weights
16.10 GB
KV cache
1.07 GB
Activations
0.81 GB
Runtime
1.80 GB
#10Gervásio 8B PTPT
8B
llama
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 8.4 GBHeadroom: 15.6 GB
126
tok/s
Estimated
Weights
4.40 GB
KV cache
2.00 GB
Activations
0.22 GB
Runtime
1.80 GB
#11StarCoder 2 7B
7B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.9 GBHeadroom: 14.1 GB
144
tok/s
Estimated
Weights
4.40 GB
KV cache
3.50 GB
Activations
0.23 GB
Runtime
1.80 GB
#12StarCoder 2 3B
3B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 5.4 GBHeadroom: 18.6 GB
336
tok/s
Estimated
Weights
2.00 GB
KV cache
1.50 GB
Activations
0.11 GB
Runtime
1.80 GB

Runs with tradeoffs
56 models

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

Qwen 2.5 Coder 32B Instruct
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 23.9 GBHeadroom: 0.1 GB
  • Tight VRAM fit — only 0.1 GB headroom left for context growth
ollama run qwen2.5-coder:32b
31
tok/s
Estimated
Weights
19.00 GB
KV cache
2.15 GB
Activations
0.96 GB
Runtime
1.80 GB
Qwen 3 30B-A3B
30B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 35.7 GBHeadroom: 7.5 GB
  • Partial CPU offload: ~33% of layers run on CPU
ollama run qwen3:30b
34
tok/s
Estimated
Weights
18.00 GB
KV cache
15.00 GB
Activations
0.91 GB
Runtime
1.80 GB
Muse Glimmer 30B
30B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 20.4 GBHeadroom: 3.6 GB
  • Tight VRAM fit — only 3.6 GB headroom left for context growth
ollama run muse-glimmer
34
tok/s
Estimated
Weights
17.00 GB
KV cache
0.71 GB
Activations
0.86 GB
Runtime
1.80 GB
Gemma 4 31B Dense
31B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 36.2 GBHeadroom: 7.0 GB
  • Partial CPU offload: ~34% of layers run on CPU
ollama run gemma4:31b
33
tok/s
Estimated
Weights
18.00 GB
KV cache
15.50 GB
Activations
0.91 GB
Runtime
1.80 GB
Qwen 3 32B
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 37.8 GBHeadroom: 5.4 GB
  • Partial CPU offload: ~36% of layers run on CPU
ollama run qwen3:32b
31
tok/s
Estimated
Weights
19.00 GB
KV cache
16.00 GB
Activations
0.96 GB
Runtime
1.80 GB
Qwen 2.5 32B Instruct
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 37.8 GBHeadroom: 5.4 GB
  • Partial CPU offload: ~36% of layers run on CPU
ollama run qwen2.5:32b
31
tok/s
Estimated
Weights
19.00 GB
KV cache
16.00 GB
Activations
0.96 GB
Runtime
1.80 GB
Qwen3 Coder 30B-A3B
30B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 36.8 GBHeadroom: 6.4 GB
  • Partial CPU offload: ~35% of layers run on CPU
ollama run qwen3-coder:30b
34
tok/s
Estimated
Weights
19.00 GB
KV cache
15.00 GB
Activations
0.96 GB
Runtime
1.80 GB
Qwen 3 Coder 32B
32B
qwen
Commercial OK
Quant: AWQ-INT4Context: 8,192VRAM: 37.8 GBHeadroom: 5.4 GB
  • Partial CPU offload: ~36% of layers run on CPU
19
tok/s
Estimated
Weights
19.00 GB
KV cache
16.00 GB
Activations
0.96 GB
Runtime
1.80 GB

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: 41 new comfortable, 73 new tradeoff

  • Qwen 3 0.6B
  • Qwen 3 1.7B
  • Gemma 3 270M
  • SmolLM2 135M Instruct

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: 80 new comfortable

  • Qwen 3 0.6B
  • Qwen 3 30B-A3B
  • Qwen 2.5 Coder 32B Instruct
  • Qwen3.6 27B

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: 93 new comfortable

  • Qwen 3 0.6B
  • Qwen 3 30B-A3B
  • Qwen 2.5 Coder 32B Instruct
  • Qwen3.6 27B

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 R1 (671B reasoning)
671B
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

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.