Slot L1 · open?Your product hereOne flat price, 30 days, no rotation.

Devices Models Tools GPUs Guides Blog Sponsor

Devices Models Tools GPUs Guides Blog Sponsor

Home/Can I Run

Can I run it?

Exact model x GPU verdicts: fit, memory math with KV-cache, estimated speed, best quant and upgrade path. Estimates, not measurements.

RTX 3060

12 GB

Qwen3 8B Q4_K_MRuns Qwen3 14B Q4_K_MSlow GPT-OSS 20B MXFP4Slow Qwen3.8 27B Q4_K_MNo Llama 3.3 70B Instruct Q4_K_MNo Qwen3.5 35B-A3B Instruct Q4_K_MNo Gemma 4 26B-A4B Q4_K_MSlow Qwen3.5 4B Instruct Q4_K_MRuns Gemma 4 E4B Q4_K_MRuns Gemma 3 4B Instruct Q4_K_MRuns Llama 3.1 8B Instruct Q4_K_MRuns Qwen3.5 9B Instruct Q4_K_MRuns Gemma 4 12B Q4_K_MRuns Mistral Nemo 12B Q4_K_MRuns Qwen3.5 9B Instruct (Q8) Q8_0Runs Gemma 4 12B (Q8) Q8_0Slow LFM2 24B-A2B Instruct Q4_K_MSlow Qwen3.5 27B Instruct Q4_K_MSlow Qwen3.6 27B Q4_K_MNo Gemma 4 31B Q4_K_MNo Qwen3.6 35B-A3B Q4_K_MNo Qwen3.8 27B (Q8) Q8_0No

Full RTX 3060 guide

RTX 4060

8 GB

Qwen3 8B Q4_K_MRuns Qwen3 14B Q4_K_MNo GPT-OSS 20B MXFP4No Qwen3.8 27B Q4_K_MNo Llama 3.3 70B Instruct Q4_K_MNo Qwen3.5 35B-A3B Instruct Q4_K_MNo Gemma 4 26B-A4B Q4_K_MNo Qwen3.5 4B Instruct Q4_K_MRuns Gemma 4 E4B Q4_K_MRuns Gemma 3 4B Instruct Q4_K_MRuns Llama 3.1 8B Instruct Q4_K_MRuns Qwen3.5 9B Instruct Q4_K_MRuns Gemma 4 12B Q4_K_MSlow Mistral Nemo 12B Q4_K_MSlow Qwen3.5 9B Instruct (Q8) Q8_0Slow Gemma 4 12B (Q8) Q8_0No LFM2 24B-A2B Instruct Q4_K_MNo Qwen3.5 27B Instruct Q4_K_MNo Qwen3.6 27B Q4_K_MNo Gemma 4 31B Q4_K_MNo Qwen3.6 35B-A3B Q4_K_MNo Qwen3.8 27B (Q8) Q8_0No

Full RTX 4060 guide

RTX 4060 Ti

16 GB

Qwen3 8B Q4_K_MRuns Qwen3 14B Q4_K_MRuns GPT-OSS 20B MXFP4Runs Qwen3.8 27B Q4_K_MSlow Llama 3.3 70B Instruct Q4_K_MNo Qwen3.5 35B-A3B Instruct Q4_K_MSlow Gemma 4 26B-A4B Q4_K_MSlow Qwen3.5 4B Instruct Q4_K_MRuns Gemma 4 E4B Q4_K_MRuns Gemma 3 4B Instruct Q4_K_MRuns Llama 3.1 8B Instruct Q4_K_MRuns Qwen3.5 9B Instruct Q4_K_MRuns Gemma 4 12B Q4_K_MRuns Mistral Nemo 12B Q4_K_MRuns Qwen3.5 9B Instruct (Q8) Q8_0Runs Gemma 4 12B (Q8) Q8_0Runs LFM2 24B-A2B Instruct Q4_K_MRuns Qwen3.5 27B Instruct Q4_K_MSlow Qwen3.6 27B Q4_K_MSlow Gemma 4 31B Q4_K_MSlow Qwen3.6 35B-A3B Q4_K_MNo Qwen3.8 27B (Q8) Q8_0No

Full RTX 4060 Ti guide

RTX 4070

12 GB

Qwen3 8B Q4_K_MRuns Qwen3 14B Q4_K_MSlow GPT-OSS 20B MXFP4Slow Qwen3.8 27B Q4_K_MNo Llama 3.3 70B Instruct Q4_K_MNo Qwen3.5 35B-A3B Instruct Q4_K_MNo Gemma 4 26B-A4B Q4_K_MSlow Qwen3.5 4B Instruct Q4_K_MRuns Gemma 4 E4B Q4_K_MRuns Gemma 3 4B Instruct Q4_K_MRuns Llama 3.1 8B Instruct Q4_K_MRuns Qwen3.5 9B Instruct Q4_K_MRuns Gemma 4 12B Q4_K_MRuns Mistral Nemo 12B Q4_K_MRuns Qwen3.5 9B Instruct (Q8) Q8_0Runs Gemma 4 12B (Q8) Q8_0Slow LFM2 24B-A2B Instruct Q4_K_MSlow Qwen3.5 27B Instruct Q4_K_MSlow Qwen3.6 27B Q4_K_MNo Gemma 4 31B Q4_K_MNo Qwen3.6 35B-A3B Q4_K_MNo Qwen3.8 27B (Q8) Q8_0No

Full RTX 4070 guide

RTX 4070 Ti SUPER

16 GB

Qwen3 8B Q4_K_MRuns Qwen3 14B Q4_K_MRuns GPT-OSS 20B MXFP4Runs Qwen3.8 27B Q4_K_MSlow Llama 3.3 70B Instruct Q4_K_MNo Qwen3.5 35B-A3B Instruct Q4_K_MSlow Gemma 4 26B-A4B Q4_K_MSlow Qwen3.5 4B Instruct Q4_K_MRuns Gemma 4 E4B Q4_K_MRuns Gemma 3 4B Instruct Q4_K_MRuns Llama 3.1 8B Instruct Q4_K_MRuns Qwen3.5 9B Instruct Q4_K_MRuns Gemma 4 12B Q4_K_MRuns Mistral Nemo 12B Q4_K_MRuns Qwen3.5 9B Instruct (Q8) Q8_0Runs Gemma 4 12B (Q8) Q8_0Runs LFM2 24B-A2B Instruct Q4_K_MRuns Qwen3.5 27B Instruct Q4_K_MSlow Qwen3.6 27B Q4_K_MSlow Gemma 4 31B Q4_K_MSlow Qwen3.6 35B-A3B Q4_K_MNo Qwen3.8 27B (Q8) Q8_0No

Full RTX 4070 Ti SUPER guide

RTX 3090

24 GB

Qwen3 8B Q4_K_MRuns Qwen3 14B Q4_K_MRuns GPT-OSS 20B MXFP4Runs Qwen3.8 27B Q4_K_MRuns Llama 3.3 70B Instruct Q4_K_MNo Qwen3.5 35B-A3B Instruct Q4_K_MRuns Gemma 4 26B-A4B Q4_K_MRuns Qwen3.5 4B Instruct Q4_K_MRuns Gemma 4 E4B Q4_K_MRuns Gemma 3 4B Instruct Q4_K_MRuns Llama 3.1 8B Instruct Q4_K_MRuns Qwen3.5 9B Instruct Q4_K_MRuns Gemma 4 12B Q4_K_MRuns Mistral Nemo 12B Q4_K_MRuns Qwen3.5 9B Instruct (Q8) Q8_0Runs Gemma 4 12B (Q8) Q8_0Runs LFM2 24B-A2B Instruct Q4_K_MRuns Qwen3.5 27B Instruct Q4_K_MRuns Qwen3.6 27B Q4_K_MRuns Gemma 4 31B Q4_K_MRuns Qwen3.6 35B-A3B Q4_K_MSlow Qwen3.8 27B (Q8) Q8_0Slow

Full RTX 3090 guide

RTX 4090

24 GB

Qwen3 8B Q4_K_MRuns Qwen3 14B Q4_K_MRuns GPT-OSS 20B MXFP4Runs Qwen3.8 27B Q4_K_MRuns Llama 3.3 70B Instruct Q4_K_MNo Qwen3.5 35B-A3B Instruct Q4_K_MRuns Gemma 4 26B-A4B Q4_K_MRuns Qwen3.5 4B Instruct Q4_K_MRuns Gemma 4 E4B Q4_K_MRuns Gemma 3 4B Instruct Q4_K_MRuns Llama 3.1 8B Instruct Q4_K_MRuns Qwen3.5 9B Instruct Q4_K_MRuns Gemma 4 12B Q4_K_MRuns Mistral Nemo 12B Q4_K_MRuns Qwen3.5 9B Instruct (Q8) Q8_0Runs Gemma 4 12B (Q8) Q8_0Runs LFM2 24B-A2B Instruct Q4_K_MRuns Qwen3.5 27B Instruct Q4_K_MRuns Qwen3.6 27B Q4_K_MRuns Gemma 4 31B Q4_K_MRuns Qwen3.6 35B-A3B Q4_K_MSlow Qwen3.8 27B (Q8) Q8_0Slow

Full RTX 4090 guide

RTX 5070 Ti

16 GB

Qwen3 8B Q4_K_MRuns Qwen3 14B Q4_K_MRuns GPT-OSS 20B MXFP4Runs Qwen3.8 27B Q4_K_MSlow Llama 3.3 70B Instruct Q4_K_MNo Qwen3.5 35B-A3B Instruct Q4_K_MSlow Gemma 4 26B-A4B Q4_K_MSlow Qwen3.5 4B Instruct Q4_K_MRuns Gemma 4 E4B Q4_K_MRuns Gemma 3 4B Instruct Q4_K_MRuns Llama 3.1 8B Instruct Q4_K_MRuns Qwen3.5 9B Instruct Q4_K_MRuns Gemma 4 12B Q4_K_MRuns Mistral Nemo 12B Q4_K_MRuns Qwen3.5 9B Instruct (Q8) Q8_0Runs Gemma 4 12B (Q8) Q8_0Runs LFM2 24B-A2B Instruct Q4_K_MRuns Qwen3.5 27B Instruct Q4_K_MSlow Qwen3.6 27B Q4_K_MSlow Gemma 4 31B Q4_K_MSlow Qwen3.6 35B-A3B Q4_K_MNo Qwen3.8 27B (Q8) Q8_0No

Full RTX 5070 Ti guide

RTX 5080

16 GB

Qwen3 8B Q4_K_MRuns Qwen3 14B Q4_K_MRuns GPT-OSS 20B MXFP4Runs Qwen3.8 27B Q4_K_MSlow Llama 3.3 70B Instruct Q4_K_MNo Qwen3.5 35B-A3B Instruct Q4_K_MSlow Gemma 4 26B-A4B Q4_K_MSlow Qwen3.5 4B Instruct Q4_K_MRuns Gemma 4 E4B Q4_K_MRuns Gemma 3 4B Instruct Q4_K_MRuns Llama 3.1 8B Instruct Q4_K_MRuns Qwen3.5 9B Instruct Q4_K_MRuns Gemma 4 12B Q4_K_MRuns Mistral Nemo 12B Q4_K_MRuns Qwen3.5 9B Instruct (Q8) Q8_0Runs Gemma 4 12B (Q8) Q8_0Runs LFM2 24B-A2B Instruct Q4_K_MRuns Qwen3.5 27B Instruct Q4_K_MSlow Qwen3.6 27B Q4_K_MSlow Gemma 4 31B Q4_K_MSlow Qwen3.6 35B-A3B Q4_K_MNo Qwen3.8 27B (Q8) Q8_0No

Full RTX 5080 guide

RTX 5090

32 GB

Qwen3 8B Q4_K_MRuns Qwen3 14B Q4_K_MRuns GPT-OSS 20B MXFP4Runs Qwen3.8 27B Q4_K_MRuns Llama 3.3 70B Instruct Q4_K_MSlow Qwen3.5 35B-A3B Instruct Q4_K_MRuns Gemma 4 26B-A4B Q4_K_MRuns Qwen3.5 4B Instruct Q4_K_MRuns Gemma 4 E4B Q4_K_MRuns Gemma 3 4B Instruct Q4_K_MRuns Llama 3.1 8B Instruct Q4_K_MRuns Qwen3.5 9B Instruct Q4_K_MRuns Gemma 4 12B Q4_K_MRuns Mistral Nemo 12B Q4_K_MRuns Qwen3.5 9B Instruct (Q8) Q8_0Runs Gemma 4 12B (Q8) Q8_0Runs LFM2 24B-A2B Instruct Q4_K_MRuns Qwen3.5 27B Instruct Q4_K_MRuns Qwen3.6 27B Q4_K_MRuns Gemma 4 31B Q4_K_MRuns Qwen3.6 35B-A3B Q4_K_MRuns Qwen3.8 27B (Q8) Q8_0Runs

Full RTX 5090 guide

Find the best local AI model for your exact hardware. Independent, open recommendations, no cloud required.

@modelfit_ hi@modelfit.io

Navigate

Contact Devices Models Use Cases Compare Quant Compare Best Hardware Benchmark

Popular

MacBook Pro Mac Mini RTX 4090 Claude Code models Coding models Qwen vs Llama

Resources

Best LLM for MacBook Best LLM for iPhone Ollama Setup Run AI Offline Key Facts & Stats Open Dataset modelfit CLI About & Disclosure Sponsor / Advertise Privacy Policy Terms of Service

As an Amazon Associate, ModelFit earns from qualifying purchases. We may also earn a commission on cloud-GPU sign-ups, at no extra cost to you.

© 2026 ModelFit · 1021 E Lincolnway, Suite 8081, Cheyenne, WY 82001, USA