NVIDIA · 2023-05
Best local LLMs for the RTX 4060 Ti 8 GB
8 GB VRAM · 288 GB/s · ~7.4 GB usable.
Check RTX 4060 Ti 8 GB price →Try it with your context & use case
Preset to the RTX 4060 Ti 8 GB. Change the context length or filter by use case.
9 models run well and 6 run tight on RTX 4060 Ti 8 GB (any context — just fitting the weights) — 7.4 GB usable.
Sort:
| Model | Size | Fit | Best quant | Needs | Memory | Speed |
|---|---|---|---|---|---|---|
| Gemma 2 9B | 9.2B | Runs well | Q5_K_M | 7.1 GB | ~32 tok/s | |
| Qwen3 8B | 8.2B | Runs well | Q6_K | 7.3 GB | ~31 tok/s | |
| Llama 3.1 8B | 8.0B | Runs well | Q6_K | 7.1 GB | ~31 tok/s | |
| Qwen2.5-Coder 7B | 7.6B | Runs well | Q6_K | 6.8 GB | ~33 tok/s | |
| Mistral 7B v0.3 | 7.3B | Runs well | Q6_K | 6.5 GB | ~35 tok/s | |
| Gemma 3 4B | 4.3B | Runs well | Q8_0 | 5.2 GB | ~45 tok/s | |
| Qwen3 4B | 4B | Runs well | Q8_0 | 4.9 GB | ~49 tok/s | |
| Llama 3.2 3B | 3.2B | Runs well | FP16 | 7.0 GB | ~32 tok/s | |
| Llama 3.2 1B | 1.2B | Runs well | FP16 | 3.2 GB | ~84 tok/s | |
| Qwen3 14B | 14.8B | Runs (tight) | Q2_K | 6.8 GB | ~33 tok/s | |
| Qwen2.5 14B | 14.8B | Runs (tight) | Q2_K | 6.8 GB | ~33 tok/s | |
| DeepSeek-R1 Distill Qwen 14B | 14.8B | Runs (tight) | Q2_K | 6.8 GB | ~33 tok/s | |
| Phi-4 14B | 14.7B | Runs (tight) | Q2_K | 6.7 GB | ~34 tok/s | |
| Mistral Nemo 12B | 12.2B | Runs (tight) | Q3_K_M | 6.5 GB | ~35 tok/s | |
| Gemma 3 12B | 12.2B | Runs (tight) | Q3_K_M | 6.5 GB | ~35 tok/s | |
| DeepSeek-R1 671B-A37B (MoE)MoE | 671B | Won't fit | — | 273 GB | — | |
| Qwen3 235B-A22B (MoE)MoE | 235B | Won't fit | — | 96 GB | — | |
| Llama 4 Scout (MoE)MoE | 109B | Won't fit | — | 45 GB | — | |
| Qwen2.5 72B | 72.7B | Won't fit | — | 30 GB | — | |
| Llama 3.3 70B | 70.6B | Won't fit | — | 29 GB | — | |
| DeepSeek-R1 Distill Llama 70B | 70.6B | Won't fit | — | 29 GB | — | |
| Mixtral 8x7B (MoE)MoE | 46.7B | Won't fit | — | 20 GB | — | |
| Qwen3 32B | 32.8B | Won't fit | — | 14 GB | — | |
| Qwen2.5 32B | 32.8B | Won't fit | — | 14 GB | — | |
| Qwen2.5-Coder 32B | 32.8B | Won't fit | — | 14 GB | — | |
| DeepSeek-R1 Distill Qwen 32B | 32.8B | Won't fit | — | 14 GB | — | |
| Qwen3 30B-A3B (MoE)MoE | 30.5B | Won't fit | — | 13 GB | — | |
| Gemma 3 27B | 27.4B | Won't fit | — | 12 GB | — | |
| Gemma 2 27B | 27.2B | Won't fit | — | 12 GB | — | |
| Mistral Small 3 24B | 23.6B | Won't fit | — | 10 GB | — |
Estimates, computed in your browser — VRAM, quantisation and speed vary with your runtime and settings. How we estimate →
Top picks for the RTX 4060 Ti 8 GB
Every model on the RTX 4060 Ti 8 GB
| Model | Size | Fit | Best quant | Needs | Speed |
|---|---|---|---|---|---|
| Qwen3 8B | 8.2B | Runs well | Q4 | 6.7 GB | ~42 tok/s |
| Llama 3.1 8B | 8.0B | Runs well | Q5 | 7.3 GB | ~36 tok/s |
| Qwen2.5-Coder 7B | 7.6B | Runs well | Q6 | 7.2 GB | ~33 tok/s |
| Mistral 7B v0.3 | 7.3B | Runs well | Q5 | 6.7 GB | ~40 tok/s |
| Gemma 3 4B | 4.3B | Runs well | Q8 | 6.2 GB | ~45 tok/s |
| Qwen3 4B | 4B | Runs well | Q8 | 6.0 GB | ~49 tok/s |
| Llama 3.2 3B | 3.2B | Runs well | Q8 | 4.9 GB | ~61 tok/s |
| Llama 3.2 1B | 1.2B | Runs well | FP16 | 3.4 GB | ~84 tok/s |
| Mistral Nemo 12B | 12.2B | Runs (tight) | Q2 | 6.9 GB | ~41 tok/s |
| Gemma 2 9B | 9.2B | Runs (tight) | Q2 | 7.1 GB | ~54 tok/s |
| DeepSeek-R1 671B-A37B (MoE)MoE | 671B | Won't fit | — | 303 GB | — |
| Qwen3 235B-A22B (MoE)MoE | 235B | Won't fit | — | 98 GB | — |
| Llama 4 Scout (MoE)MoE | 109B | Won't fit | — | 46 GB | — |
| Qwen2.5 72B | 72.7B | Won't fit | — | 33 GB | — |
| Llama 3.3 70B | 70.6B | Won't fit | — | 32 GB | — |
| DeepSeek-R1 Distill Llama 70B | 70.6B | Won't fit | — | 32 GB | — |
| Mixtral 8x7B (MoE)MoE | 46.7B | Won't fit | — | 21 GB | — |
| Qwen3 32B | 32.8B | Won't fit | — | 16 GB | — |
| Qwen2.5 32B | 32.8B | Won't fit | — | 16 GB | — |
| Qwen2.5-Coder 32B | 32.8B | Won't fit | — | 16 GB | — |
| DeepSeek-R1 Distill Qwen 32B | 32.8B | Won't fit | — | 16 GB | — |
| Qwen3 30B-A3B (MoE)MoE | 30.5B | Won't fit | — | 14 GB | — |
| Gemma 3 27B | 27.4B | Won't fit | — | 16 GB | — |
| Gemma 2 27B | 27.2B | Won't fit | — | 15 GB | — |
| Mistral Small 3 24B | 23.6B | Won't fit | — | 12 GB | — |
| Qwen3 14B | 14.8B | Won't fit | — | 8.0 GB | — |
| Qwen2.5 14B | 14.8B | Won't fit | — | 8.3 GB | — |
| DeepSeek-R1 Distill Qwen 14B | 14.8B | Won't fit | — | 8.3 GB | — |
| Phi-4 14B | 14.7B | Won't fit | — | 8.3 GB | — |
| Gemma 3 12B | 12.2B | Won't fit | — | 8.7 GB | — |
Similar hardware
FAQ
What is the best LLM for the RTX 4060 Ti 8 GB?
For general use, Qwen3 8B is the strongest model that runs well on the RTX 4060 Ti 8 GB. See the picks-by-use-case below for coding, reasoning and more.
How much can the RTX 4060 Ti 8 GB run?
The RTX 4060 Ti 8 GB has 8 GB of VRAM, of which about 7.4 GB is usable for a model. That runs 8 of our tracked models well and 2 more at a tight quantisation.
Estimates at 8K context — see how we compute these.