Best local AI models for GeForce RTX 3090
The value pick: the same 24 GB as a 4090 at a fraction of the price, roughly 60–70% of the throughput.
Specification
VRAM24 GB
Usable for models23 GB
System RAM32 GB
Bandwidth936 GB/s
Local trainingSupported
Operating systemswindows, linux
Runs well
29 models fit this machine
Estimated
| Model | Params | Quantization | Memory | ~tok/s | Fit | Fine-tune |
|---|---|---|---|---|---|---|
| Qwen2.5 14B Instruct | 14.8B | Q6_K | 14 GB | 60 | Excellent fit | Yes |
| Mistral Small 24B Instruct | 23.6B | Q4_K_M | 16 GB | 51 | Good fit | Yes |
| Phi-4 14B | 14.7B | Q8_0 | 17 GB | 46 | Good fit | Yes |
| Mistral Nemo 12B Instruct | 12.2B | Q6_K | 12 GB | 72 | Excellent fit | Yes |
| Qwen3 14B | 14.8B | Q6_K | 13 GB | 60 | Excellent fit | Yes |
| DeepSeek-R1-Distill-Qwen-14B | 14.8B | Q6_K | 14 GB | 60 | Excellent fit | Yes |
| Qwen2.5 Coder 32B Instruct | 32.8B | Q4_K_M | 21 GB | 37 | Tight fit | Yes |
| Gemma 2 9B Instruct | 9.2B | Q8_0 | 12 GB | 74 | Excellent fit | Yes |
| DeepSeek-Coder-V2-Lite Instruct | 15.7B | Q5_K_M | 13 GB | 425 | Excellent fit | Yes |
| StarCoder2 15B | 16B | Q8_0 | 17 GB | 43 | Good fit | Yes |
| Qwen2.5 32B Instruct | 32.8B | Q4_K_M | 21 GB | 37 | Tight fit | Yes |
| Qwen2.5 Coder 7B Instruct | 7.6B | F16 | 15 GB | 48 | Good fit | Yes |
| Llama 3.1 8B Instruct | 8B | Q8_0 | 9.5 GB | 85 | Excellent fit | Yes |
| Gemma 3 12B Instruct | 12.2B | Q8_0 | 16 GB | 56 | Good fit | Yes |
| Qwen3 8B | 8.2B | Q8_0 | 9.8 GB | 83 | Excellent fit | Yes |
| Qwen2.5 7B Instruct | 7.6B | F16 | 15 GB | 48 | Good fit | Yes |
| DeepSeek-R1-Distill-Qwen-32B | 32.8B | Q4_K_M | 21 GB | 37 | Tight fit | Yes |
| Code Llama 7B Instruct | 6.7B | Q8_0 | 11 GB | 102 | Excellent fit | Yes |
Fine-tunable here
Models you can train on this machine
Qwen2.5 14B Instruct
QLORA · 12 GB peak
Mistral Small 24B Instruct
QLORA · 17 GB peak
Phi-4 14B
QLORA · 12 GB peak
Mistral Nemo 12B Instruct
QLORA · 10 GB peak
Qwen3 14B
QLORA · 12 GB peak
DeepSeek-R1-Distill-Qwen-14B
QLORA · 12 GB peak
Qwen2.5 Coder 32B Instruct
QLORA · 22 GB peak
Gemma 2 9B Instruct
QLORA · 8.2 GB peak