What can NVIDIA GeForce RTX 5090 run locally?

34 models fit comfortably on NVIDIA GeForce RTX 5090 with 32 GB system RAM. 13 more run with tradeoffs. Top pick: Gemma 3 1B.

What's the recommended runner for this hardware?

llama.cpp / Ollama (CUDA). This is the runner that gives best tokens-per-second on NVIDIA GeForce RTX 5090 based on windows support and the GPU backend.

What can NVIDIA GeForce RTX 5090 run for coding?

Build: NVIDIA GeForce RTX 5090 + — + 32 GB RAM (windows)

Memory: 32 GB VRAM + 32 GB system RAM

Runner: llama.cpp / Ollama (CUDA)

Any Chat Coding Agents Reasoning Vision Long context Creative

Runs comfortably
34 models

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

#1Gemma 3 1B

gemma

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 11.1 GBHeadroom: 20.9 GBTTFT: instant

ollama run gemma3:1b

1929

tok/s

Weights

0.60 GB

KV cache

0.50 GB

Activations

8.22 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~20 ms (instant)

Model details →Run-on benchmark page →

#2Llama 3.2 1B Instruct

llama

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 11.6 GBHeadroom: 20.4 GBTTFT: instant

ollama run llama3.2:1b

1096

tok/s

Weights

1.06 GB

KV cache

0.50 GB

Activations

8.25 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~20 ms (instant)

Model details →Run-on benchmark page →

#3Gemma 4 E2B (Effective 2B)

gemma

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 13.2 GBHeadroom: 18.8 GBTTFT: instant

ollama run gemma4:e2b

548

tok/s

Weights

2.13 GB

KV cache

1.00 GB

Activations

8.30 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~41 ms (instant)

Model details →Run-on benchmark page →

#4Phi-3.5 Vision

4.2B

phi

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 14.8 GBHeadroom: 17.2 GBTTFT: instant

459

tok/s

Weights

2.54 GB

KV cache

2.10 GB

Activations

8.32 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~86 ms (instant)

Model details →Run-on benchmark page →

#5CodeGemma 7B

gemma

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 17.9 GBHeadroom: 14.1 GBTTFT: fast

ollama run codegemma:7b

276

tok/s

Weights

4.23 GB

KV cache

3.50 GB

Activations

8.40 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~143 ms (fast)

Model details →Run-on benchmark page →

#6Llama 3.2 3B Instruct

llama

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 14.8 GBHeadroom: 17.2 GBTTFT: instant

ollama run llama3.2:3b

365

tok/s

Weights

3.19 GB

KV cache

1.50 GB

Activations

8.35 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~61 ms (instant)

Model details →Run-on benchmark page →

#7Phi-3.5 Mini Instruct

3.8B

phi

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 16.1 GBHeadroom: 15.9 GBTTFT: instant

ollama run phi3.5:3.8b

288

tok/s

Weights

4.04 GB

KV cache

1.90 GB

Activations

8.39 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~78 ms (instant)

Model details →Run-on benchmark page →

#8Gemma 4 E4B (Effective 4B)

gemma

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 16.5 GBHeadroom: 15.5 GBTTFT: instant

ollama run gemma4:e4b

274

tok/s

Weights

4.25 GB

KV cache

2.00 GB

Activations

8.40 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~82 ms (instant)

Model details →Run-on benchmark page →

#9Qwen 3 4B

qwen

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 16.5 GBHeadroom: 15.5 GBTTFT: instant

ollama run qwen3:4b

274

tok/s

Weights

4.25 GB

KV cache

2.00 GB

Activations

8.40 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~82 ms (instant)

Model details →Run-on benchmark page →

#10Gemma 3 4B

gemma

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 16.5 GBHeadroom: 15.5 GBTTFT: instant

ollama run gemma3:4b

274

tok/s

Weights

4.25 GB

KV cache

2.00 GB

Activations

8.40 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~82 ms (instant)

Model details →Run-on benchmark page →

#11Mistral 7B Instruct v0.3

mistral

Commercial OK

Quant: Q5_K_MContext: 8,192VRAM: 18.5 GBHeadroom: 13.5 GBTTFT: fast

ollama run mistral:7b

242

tok/s

Weights

4.81 GB

KV cache

3.50 GB

Activations

8.43 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~143 ms (fast)

Model details →Run-on benchmark page →

#12Llama 3.1 Nemotron Nano 8B

llama

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 19.1 GBHeadroom: 12.9 GBTTFT: fast

241

tok/s

Weights

4.83 GB

KV cache

4.00 GB

Activations

8.43 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~164 ms (fast)

Model details →Run-on benchmark page →

Runs with tradeoffs
13 models

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

DeepSeek Coder V2 Lite (16B)

16B

deepseek

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 28.1 GBHeadroom: 3.9 GBTTFT: fast

• Tight VRAM fit — only 3.9 GB headroom left for context growth

ollama run deepseek-coder-v2:16b

121

tok/s

Weights

9.66 GB

KV cache

8.00 GB

Activations

8.68 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~328 ms (fast)

Model details →Run-on benchmark page →

Qwen 3 32B

32B

qwen

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 28.1 GBHeadroom: 3.9 GBTTFT: noticeable

• Tight VRAM fit — only 3.9 GB headroom left for context growth

ollama run qwen3:32b

tok/s

Weights

19.32 GB

KV cache

4.00 GB

Activations

3.01 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~655 ms (noticeable)

Model details →Run-on benchmark page →

Qwen 2.5 32B Instruct

32B

qwen

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 28.1 GBHeadroom: 3.9 GBTTFT: noticeable

• Tight VRAM fit — only 3.9 GB headroom left for context growth

ollama run qwen2.5:32b

tok/s

Weights

19.32 GB

KV cache

4.00 GB

Activations

3.01 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~655 ms (noticeable)

Model details →Run-on benchmark page →

Mistral Nemo 12B Instruct

12B

mistral

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 29.4 GBHeadroom: 2.6 GBTTFT: fast

• Tight VRAM fit — only 2.6 GB headroom left for context growth

ollama run mistral-nemo:12b

tok/s

Weights

12.75 GB

KV cache

6.00 GB

Activations

8.83 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~246 ms (fast)

Model details →Run-on benchmark page →

Gemma 3 12B

12B

gemma

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 29.4 GBHeadroom: 2.6 GBTTFT: fast

• Tight VRAM fit — only 2.6 GB headroom left for context growth

ollama run gemma3:12b

tok/s

Weights

12.75 GB

KV cache

6.00 GB

Activations

8.83 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~246 ms (fast)

Model details →Run-on benchmark page →

Pixtral 12B

12B

mistral

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 29.4 GBHeadroom: 2.6 GBTTFT: fast

• Tight VRAM fit — only 2.6 GB headroom left for context growth

ollama run pixtral:12b

tok/s

Weights

12.75 GB

KV cache

6.00 GB

Activations

8.83 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~246 ms (fast)

Model details →Run-on benchmark page →

Llama 3.3 70B Instruct

70B

llama

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 48.9 GBHeadroom: 2.3 GBTTFT: noticeable

• Partial CPU offload: ~35% of layers run on CPU

ollama run llama3.3:70b

tok/s

Weights

42.26 GB

KV cache

0.67 GB

Activations

4.16 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~1434 ms (noticeable)

Model details →Run-on benchmark page →

DeepSeek R1 Distill Qwen 32B

32B

deepseek

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 28.1 GBHeadroom: 3.9 GBTTFT: noticeable

• Tight VRAM fit — only 3.9 GB headroom left for context growth

ollama run deepseek-r1:32b

tok/s

Weights

19.32 GB

KV cache

4.00 GB

Activations

3.01 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~655 ms (noticeable)

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: 18 new tradeoff

• Llama 3.3 70B Instruct
• Qwen 3 32B
• DeepSeek R1 Distill Llama 70B
• DeepSeek R1 Distill Qwen 32B

Shop this upgrade↗

Upgrade to NVIDIA A100 40GB

see current pricing

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

Unlocks: 11 new comfortable

• DeepSeek Coder V2 Lite (16B)
• Mistral Nemo 12B Instruct
• Gemma 3 12B
• Pixtral 12B

Shop this upgrade↗

Add a second NVIDIA GeForce RTX 5090

~$2499

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: 13 new comfortable

• DeepSeek Coder V2 Lite (16B)
• Mistral Nemo 12B Instruct
• Gemma 3 12B
• Pixtral 12B

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.

Qwen 3 235B-A22B

235B

qwen

Commercial OK