What can NVIDIA GeForce RTX 5090 run locally?

207 models fit comfortably on NVIDIA GeForce RTX 5090 with 32 GB system RAM. 26 more run with tradeoffs. Top pick: Qwen 3 0.6B.

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 chat?

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
207 models

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

#1Qwen 3 0.6B

0.6B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 2.4 GBHeadroom: 29.6 GBTTFT: instant

3215

tok/s

Estimated

Weights

0.30 GB

KV cache

0.30 GB

Activations

0.02 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~12 ms (instant)

Model details →

#2Qwen 3 8B

qwen

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 14.4 GBHeadroom: 17.6 GBTTFT: fast

ollama run qwen3:8b

137

tok/s

Estimated

Weights

8.20 GB

KV cache

4.00 GB

Activations

0.42 GB

Runtime

1.80 GB

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

Model details →

#3Llama 3.2 3B Instruct

llama

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 6.9 GBHeadroom: 25.1 GBTTFT: instant

ollama run llama3.2:3b

365

tok/s

Estimated

Weights

3.40 GB

KV cache

1.50 GB

Activations

0.18 GB

Runtime

1.80 GB

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

Model details →

#4Qwen 3 1.7B

1.7B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 3.6 GBHeadroom: 28.4 GBTTFT: instant

1135

tok/s

Estimated

Weights

0.90 GB

KV cache

0.85 GB

Activations

0.05 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~35 ms (instant)

Model details →

#5Dolphin 3.0 8B

dolphin

Commercial OK

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

ollama run dolphin3:8b

241

tok/s

Estimated

Weights

5.00 GB

KV cache

4.00 GB

Activations

0.26 GB

Runtime

1.80 GB

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

Model details →

#6TinyLlama 1.1B Chat v1.0

1.1B

llama

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 2.6 GBHeadroom: 29.4 GBTTFT: instant

1754

tok/s

Estimated

Weights

0.60 GB

KV cache

0.14 GB

Activations

0.03 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~23 ms (instant)

Model details →

#7Gemma 2 2B Instruct

gemma

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 4.0 GBHeadroom: 28.0 GBTTFT: instant

965

tok/s

Estimated

Weights

1.10 GB

KV cache

1.00 GB

Activations

0.06 GB

Runtime

1.80 GB

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

Model details →

#8Mistral 7B Instruct v0.3

mistral

Commercial OK

Quant: Q5_K_MContext: 8,192VRAM: 10.7 GBHeadroom: 21.3 GBTTFT: fast

ollama run mistral:7b

242

tok/s

Estimated

Weights

5.10 GB

KV cache

3.50 GB

Activations

0.26 GB

Runtime

1.80 GB

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

Model details →

#9DeepSeek V2 Lite Chat

15.7B

deepseek

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 18.7 GBHeadroom: 13.3 GBTTFT: instant

804

tok/s

Estimated

Weights

8.60 GB

KV cache

7.85 GB

Activations

0.44 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~49 ms (instant)

Model details →

#10Gemma 2 9B Instruct

gemma

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 16.6 GBHeadroom: 15.4 GBTTFT: fast

ollama run gemma2:9b

122

tok/s

Estimated

Weights

9.80 GB

KV cache

4.50 GB

Activations

0.50 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~184 ms (fast)

Model details →

#11Trendyol LLM 7B Chat v0.1

llama

Quant: Q4_K_MContext: 4,096VRAM: 7.6 GBHeadroom: 24.4 GBTTFT: fast

276

tok/s

Estimated

Weights

3.90 GB

KV cache

1.75 GB

Activations

0.20 GB

Runtime

1.80 GB

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

Model details →

#12Kumru 2B

2.4B

mistral

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 4.6 GBHeadroom: 27.4 GBTTFT: instant

ollama run alibayram/kumru:latest

804

tok/s

Estimated

Weights

1.50 GB

KV cache

1.20 GB

Activations

0.08 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~49 ms (instant)

Model details →

Runs with tradeoffs
26 models

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

Mistral Small 3 24B

24B

mistral

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 28.5 GBHeadroom: 3.5 GBTTFT: fast

• Tight VRAM fit — only 3.5 GB headroom left for context growth

ollama run mistral-small:24b

tok/s

Estimated

Weights

14.00 GB

KV cache

12.00 GB

Activations

0.71 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~492 ms (fast)

Model details →

Mistral Small 3.2 24B

24B

mistral

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 28.5 GBHeadroom: 3.5 GBTTFT: fast

• Tight VRAM fit — only 3.5 GB headroom left for context growth

tok/s

Estimated

Weights

14.00 GB

KV cache

12.00 GB

Activations

0.71 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~492 ms (fast)

Model details →

Mistral Medium 3 24B (dense)

24B

mistral

Quant: Q4_K_MContext: 8,192VRAM: 28.5 GBHeadroom: 3.5 GBTTFT: fast

• Tight VRAM fit — only 3.5 GB headroom left for context growth

tok/s

Estimated

Weights

14.00 GB

KV cache

12.00 GB

Activations

0.71 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~492 ms (fast)

Model details →

Gemma 4 26B MoE

26B

gemma

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 31.6 GBHeadroom: 0.4 GBTTFT: noticeable

• Tight VRAM fit — only 0.4 GB headroom left for context growth

ollama run gemma4:26b-moe

tok/s

Estimated

Weights

16.00 GB

KV cache

13.00 GB

Activations

0.81 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~532 ms (noticeable)

Model details →

ALIA 40b instruct 2601

40B

llama

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 29.9 GBHeadroom: 2.1 GBTTFT: noticeable

• Tight VRAM fit — only 2.1 GB headroom left for context growth

tok/s

Estimated

Weights

22.00 GB

KV cache

5.00 GB

Activations

1.10 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~819 ms (noticeable)

Model details →

Falcon 40B Instruct

40B

falcon

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 29.9 GBHeadroom: 2.1 GBTTFT: noticeable

• Tight VRAM fit — only 2.1 GB headroom left for context growth

tok/s

Estimated

Weights

22.00 GB

KV cache

5.00 GB

Activations

1.10 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~819 ms (noticeable)

Model details →

Mixtral 8x7B Instruct

47B

mixtral

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 37.1 GBHeadroom: 14.1 GBTTFT: noticeable

• Partial CPU offload: ~14% of layers run on CPU

ollama run mixtral:8x7b

tok/s

Estimated

Weights

28.00 GB

KV cache

5.88 GB

Activations

1.40 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~963 ms (noticeable)

Model details →

Hermes 4 70B FP8

70B

llama

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 51.0 GBHeadroom: 0.2 GBTTFT: noticeable

• Partial CPU offload: ~37% of layers run on CPU

tok/s

Estimated

Weights

38.50 GB

KV cache

8.75 GB

Activations

1.93 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~1434 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: 9 new comfortable, 43 new tradeoff

• Gemma 3 270M
• SmolLM2 135M Instruct
• SmolLM2 360M Instruct
• VBART Large (Turkish Summarization)

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 ~1555 GB/s.

Unlocks: 30 new comfortable

• Qwen3.6 35B-A3B
• Gemma 4 26B MoE
• Gemma 4 26B-A4B
• Gemma 3 270M

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: 48 new comfortable

• Llama 3.3 70B Instruct
• DeepSeek R1 Distill Llama 70B
• Qwen3.6 35B-A3B
• 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