What can NVIDIA GeForce RTX 4090 run locally?

20 models fit comfortably on NVIDIA GeForce RTX 4090 with 32 GB system RAM. 26 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 4090 based on windows support and the GPU backend.

What can NVIDIA GeForce RTX 4090 run for agents?

Build: NVIDIA GeForce RTX 4090 + — + 32 GB RAM (windows)

Memory: 24 GB VRAM + 32 GB system RAM

Runner: llama.cpp / Ollama (CUDA)

Any Chat Coding Agents Reasoning Vision Long context Creative

Runs comfortably
20 models

Ranked by fit for agents 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: 12.9 GBTTFT: instant

ollama run gemma3:1b

1085

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): ~31 ms (instant)

Model details →Run-on benchmark page →

#2Llama 3.2 1B Instruct

llama

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 11.6 GBHeadroom: 12.4 GBTTFT: instant

ollama run llama3.2:1b

617

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): ~31 ms (instant)

Model details →Run-on benchmark page →

#3Gemma 4 E2B (Effective 2B)

gemma

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 13.2 GBHeadroom: 10.8 GBTTFT: instant

ollama run gemma4:e2b

308

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): ~62 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: 9.2 GBTTFT: fast

258

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): ~130 ms (fast)

Model details →Run-on benchmark page →

#5Llama 3.2 3B Instruct

llama

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 14.8 GBHeadroom: 9.2 GBTTFT: instant

ollama run llama3.2:3b

206

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): ~93 ms (instant)

Model details →Run-on benchmark page →

#6Mistral 7B Instruct v0.3

mistral

Commercial OK

Quant: Q5_K_MContext: 8,192VRAM: 18.5 GBHeadroom: 5.5 GBTTFT: fast

ollama run mistral:7b

136

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): ~217 ms (fast)

Model details →Run-on benchmark page →

#7Llama 3.1 Nemotron Nano 8B

llama

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 19.1 GBHeadroom: 4.9 GBTTFT: fast

136

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): ~248 ms (fast)

Model details →Run-on benchmark page →

#8Qwen 3 4B

qwen

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 16.5 GBHeadroom: 7.5 GBTTFT: fast

ollama run qwen3:4b

154

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): ~124 ms (fast)

Model details →Run-on benchmark page →

#9Phi-3.5 Mini Instruct

3.8B

phi

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 16.1 GBHeadroom: 7.9 GBTTFT: fast

ollama run phi3.5:3.8b

162

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): ~118 ms (fast)

Model details →Run-on benchmark page →

#10Qwen 2.5 7B Instruct

qwen

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 18.3 GBHeadroom: 5.7 GBTTFT: fast

ollama run qwen2.5:7b

tok/s

Weights

7.44 GB

KV cache

0.47 GB

Activations

8.56 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~217 ms (fast)

Model details →Run-on benchmark page →

#11CodeGemma 7B

gemma

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 17.9 GBHeadroom: 6.1 GBTTFT: fast

ollama run codegemma:7b

155

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): ~217 ms (fast)

Model details →Run-on benchmark page →

#12Gemma 4 E4B (Effective 4B)

gemma

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 16.5 GBHeadroom: 7.5 GBTTFT: fast

ollama run gemma4:e4b

154

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): ~124 ms (fast)

Model details →Run-on benchmark page →

Runs with tradeoffs
26 models

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

Hermes 3 Llama 3.1 8B

hermes

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 22.9 GBHeadroom: 1.1 GBTTFT: fast

• Tight VRAM fit — only 1.1 GB headroom left for context growth

ollama run hermes3:8b

tok/s

Weights

8.50 GB

KV cache

4.00 GB

Activations

8.62 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~248 ms (fast)

Model details →Run-on benchmark page →

Gemma 2 9B Instruct

gemma

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 20.2 GBHeadroom: 3.8 GBTTFT: fast

• Tight VRAM fit — only 3.8 GB headroom left for context growth

ollama run gemma2:9b

121

tok/s

Weights

5.43 GB

KV cache

4.50 GB

Activations

8.46 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~279 ms (fast)

Model details →Run-on benchmark page →

Dolphin 3.0 Mistral 24B

24B

dolphin

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 22.1 GBHeadroom: 1.9 GBTTFT: noticeable

• Tight VRAM fit — only 1.9 GB headroom left for context growth

ollama run dolphin-mistral:24b

tok/s

Weights

14.49 GB

KV cache

3.00 GB

Activations

2.77 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~744 ms (noticeable)

Model details →Run-on benchmark page →

Qwen 3 30B-A3B

30B

qwen

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 26.6 GBHeadroom: 16.6 GBTTFT: noticeable

• Partial CPU offload: ~10% of layers run on CPU

ollama run qwen3:30b

tok/s

Weights

18.11 GB

KV cache

3.75 GB

Activations

2.95 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~930 ms (noticeable)

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: 10.8 GBTTFT: noticeable

• Partial CPU offload: ~26% of layers run on CPU

ollama run qwen2.5-coder:32b

tok/s

Weights

19.32 GB

KV cache

2.15 GB

Activations

9.16 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~992 ms (noticeable)

Model details →Run-on benchmark page →

Qwen 3 32B

32B

qwen

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 28.1 GBHeadroom: 15.1 GBTTFT: noticeable

• Partial CPU offload: ~15% of layers run on CPU

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): ~992 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: 15.1 GBTTFT: noticeable

• Partial CPU offload: ~15% of layers run on CPU

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): ~992 ms (noticeable)

Model details →Run-on benchmark page →

Nemotron 3 Nano (30B-A3B)

30B

other

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 26.6 GBHeadroom: 16.6 GBTTFT: noticeable

• Partial CPU offload: ~10% of layers run on CPU

ollama run nemotron3:nano

tok/s

Weights

18.11 GB

KV cache

3.75 GB

Activations

2.95 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~930 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: 32 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 5000 Ada Generation

see current pricing

32 GB VRAM (vs your 24 GB) plus a bandwidth jump from ~1008 GB/s to ~? GB/s.

Unlocks: 15 new comfortable

• DeepSeek R1 Distill Qwen 7B
• Qwen 3 8B
• Hermes 3 Llama 3.1 8B
• Gemma 2 9B Instruct

Shop this upgrade↗

Add a second NVIDIA GeForce RTX 4090

~$1899

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: 16 new comfortable

• DeepSeek R1 Distill Qwen 7B
• Qwen 3 8B
• Hermes 3 Llama 3.1 8B
• Gemma 2 9B 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.

Qwen 3 235B-A22B

235B

qwen

Commercial OK