NVIDIA graphics card
What AI models can the NVIDIA GeForce RTX 5060 8 GB run?
At 4-bit quantization with an 8K-token conversation, 19 of the 146 open-weight models in our directory fit entirely in the NVIDIA GeForce RTX 5060 8 GB's 8 GB of video memory (about 7.4 GB usable), up to Qwen3.5 9B. With 32 GB of dual-channel DDR5-5600, 42 more run partly from system RAM, more slowly. Among models of 7B parameters or more, Qwen2.5 7B Instruct is the fastest, at an estimated 65 to 84 tokens per second.
| Model | Parameters | Memory needed | Estimated speed |
|---|---|---|---|
| Runs entirely in fast memory (19) | |||
| Qwen3.5 9B Alibaba (Qwen) | 9.7B | 6.9 GB 5.9 GB + 0.3 GB cache | 54–69 tokens/s Fast, little memory to spare |
| Moondream 3.1 Moondream | 9.3B | 6.4 GB weights only | Speed not estimated (architecture not public) |
| Moondream 3 Preview Moondream | 9.3B | 6.4 GB weights only | Speed not estimated (architecture not public) |
| Ministral 3 8B Mistral AI | 8.9B | 7.3 GB 5.4 GB + 1.1 GB cache | 54–70 tokens/s Fast, little memory to spare |
| Qwen3 VL 8B Instruct Alibaba (Qwen) | 8.8B | 7.3 GB 5.3 GB + 1.2 GB cache | 54–70 tokens/s Fast, little memory to spare |
| Qwen3 VL 8B Thinking Alibaba (Qwen) | 8.8B | 7.3 GB 5.3 GB + 1.2 GB cache | 54–70 tokens/s Fast, little memory to spare |
| UI-TARS 7B Bytedance | 8.3B | 6.3 GB 5.0 GB + 0.5 GB cache | 60–78 tokens/s Fast |
| Qwen3 8B Alibaba (Qwen) | 8.2B | 7.0 GB 5.0 GB + 1.2 GB cache | 57–74 tokens/s Fast, little memory to spare |
| Llama 3.1 8B Instruct fp8 Meta | 8.0B | 5.7 GB weights only | Speed not estimated (architecture not public) |
| Hy-MT2-7B Tencent (Hunyuan) | 8.0B | 6.7 GB 4.9 GB + 1.1 GB cache | 59–76 tokens/s Fast |
| Qwen2.5 7B Instruct Alibaba (Qwen) | 7.6B | 5.9 GB 4.6 GB + 0.5 GB cache | 65–84 tokens/s Fast |
| Gemma 3 4B IT Google DeepMind | 4.3B | 3.4 GB weights only | Speed not estimated (architecture not public) |
| Nemotron 3.5 Content Safety (free) NVIDIA | 4.3B | 3.7 GB 2.6 GB + 0.3 GB cache | 109–141 tokens/s Fast |
| Ministral 3 3B Mistral AI | 3.8B | 4.0 GB 2.3 GB + 0.9 GB cache | 108–140 tokens/s Fast |
| Llama 3.2 3B Instruct Meta | 3.2B | 2.7 GB weights only | Speed not estimated (architecture not public) |
| Granite 4.0 Micro IBM | 3.2B | 2.8 GB 1.9 GB + 0.1 GB cache | 145–187 tokens/s Fast |
| Hy-MT2-1.8B Tencent (Hunyuan) | 2.0B | 2.6 GB 1.2 GB + 0.5 GB cache | 180–233 tokens/s Fast |
| Hy-MT2-1.8B Tencent (Hunyuan) | 2.0B | 2.6 GB 1.2 GB + 0.5 GB cache | 180–233 tokens/s Fast |
| Llama 3.2 1B Instruct Meta | 1.2B | 1.5 GB weights only | Speed not estimated (architecture not public) |
| Runs, partly from system RAM (slower) (42) | |||
| Skyfall 36B V2 Thedrummer | 36.9B | 25 GB 22 GB + 2.1 GB cache | 1.7–2.3 tokens/s Too slow for chat, 18 GB in system RAM |
| Qwen3.5 35B-A3B Alibaba (Qwen) | 36.0B 4.7B active | 23 GB 22 GB + 0.2 GB cache | 38–52 tokens/s Fast, 15 GB in system RAM |
| Qwen3.6 35B-A3B Alibaba (Qwen) | 36.0B 4.7B active | 23 GB 22 GB + 0.2 GB cache | 38–52 tokens/s Fast, 15 GB in system RAM |
| Nex-N2.5-Mini NEX AGI | 35.1B 3.9B active | 22 GB 21 GB + 0.2 GB cache | 42–57 tokens/s Fast, 15 GB in system RAM |
| Laguna XS 2.1 (free) Poolside | 33.4B 2.2B active | 21 GB 20 GB + 0.4 GB cache | 50–69 tokens/s Fast, 14 GB in system RAM |
| Qwen3 VL 32B Instruct Alibaba (Qwen) | 33.4B | 23 GB 20 GB + 2.1 GB cache | 1.9–2.6 tokens/s Too slow for chat, 16 GB in system RAM |
| Qwen2.5 Coder 32B Instruct Alibaba (Qwen) | 32.8B | 23 GB 20 GB + 2.1 GB cache | 2.0–2.7 tokens/s Too slow for chat, 15 GB in system RAM |
| Qwen3 32B Alibaba (Qwen) | 32.8B | 23 GB 20 GB + 2.1 GB cache | 2.0–2.7 tokens/s Too slow for chat, 15 GB in system RAM |
| Nemotron 3 Nano 30B A3B NVIDIA | 31.6B | 20 GB 19 GB + 0.1 GB cache | 13 GB in system RAM; Speed not estimated for this architecture |
| Nemotron 3.5 Lightning 30B A3B NVIDIA | 31.6B | 20 GB 19 GB + 0.4 GB cache | 13 GB in system RAM; Speed not estimated for this architecture |
| Gemma 4 31B IT Google DeepMind | 31.3B | 22 GB 19 GB + 2.2 GB cache | 2.1–2.8 tokens/s Too slow for chat, 15 GB in system RAM |
| GLM-4.7-Flash Zhipu AI (Z.ai) | 31.2B 5.2B active | 20 GB 19 GB + 0.4 GB cache | 27–37 tokens/s Fast, 13 GB in system RAM |
| Qwen3 VL 30B A3B Instruct Alibaba (Qwen) | 31.1B 3.9B active | 20 GB 19 GB + 0.8 GB cache | 29–39 tokens/s Fast, 13 GB in system RAM |
| Qwen3 VL 30B A3B Thinking Alibaba (Qwen) | 31.1B 3.9B active | 20 GB 19 GB + 0.8 GB cache | 29–39 tokens/s Fast, 13 GB in system RAM |
| Qwen3-Coder 30B-A3B Instruct Alibaba (Qwen) | 30.5B 3.4B active | 20 GB 19 GB + 0.8 GB cache | 30–42 tokens/s Fast, 13 GB in system RAM |
| Qwen3 30B A3B Instruct 2507 Alibaba (Qwen) | 30.5B 3.4B active | 20 GB 19 GB + 0.8 GB cache | 30–42 tokens/s Fast, 13 GB in system RAM |
| Qwen3 30B A3B Thinking 2507 Alibaba (Qwen) | 30.5B 3.4B active | 20 GB 19 GB + 0.8 GB cache | 30–42 tokens/s Fast, 13 GB in system RAM |
| Qwen3 30B A3B Alibaba (Qwen) | 30.5B 3.4B active | 20 GB 19 GB + 0.8 GB cache | 30–42 tokens/s Fast, 13 GB in system RAM |
| Hy-MT2-30B-A3B Tencent (Hunyuan) | 30.1B 3.5B active | 20 GB 18 GB + 0.8 GB cache | 30–42 tokens/s Fast, 12 GB in system RAM |
| Muse Glimmer 30B Meta | 29.8B | 19 GB 18 GB + 0.2 GB cache | 2.5–3.5 tokens/s Too slow for chat, 12 GB in system RAM |
| Qwen3.8 27B Alibaba (Qwen) | 27.8B | 18 GB 17 GB + 0.5 GB cache | 2.7–3.7 tokens/s Too slow for chat, 11 GB in system RAM |
| Qwen3.5 27B Alibaba (Qwen) | 27.8B | 18 GB 17 GB + 0.5 GB cache | 2.7–3.7 tokens/s Too slow for chat, 11 GB in system RAM |
| Qwen3.6 27B Alibaba (Qwen) | 27.8B | 18 GB 17 GB + 0.5 GB cache | 2.7–3.7 tokens/s Too slow for chat, 11 GB in system RAM |
| Gemma 3 27B IT Google DeepMind | 27.4B | 17 GB weights only | 10 GB in system RAM; Speed not estimated (architecture not public) |
| Gemma 2 27B Google DeepMind | 27.2B | 17 GB weights only | 9.9 GB in system RAM; Speed not estimated (architecture not public) |
| Gemma 4 26B A4B IT Google DeepMind | 25.8B | 17 GB 16 GB + 0.5 GB cache | 9.6 GB in system RAM; Speed not estimated for this architecture |
| Voxtral Small 24B 2507 Mistral AI | 24.3B | 17 GB 15 GB + 1.3 GB cache | 3.1–4.2 tokens/s Too slow for chat, 9.5 GB in system RAM |
| Uncensored Cognitivecomputations | 24.0B | 17 GB 15 GB + 1.3 GB cache | 3.1–4.3 tokens/s Too slow for chat, 9.3 GB in system RAM |
| Mistral Small 3.1 24B Instruct Mistral AI | 24.0B | 17 GB 15 GB + 1.3 GB cache | 3.1–4.3 tokens/s Too slow for chat, 9.3 GB in system RAM |
| LFM2.5-24B-A2B Liquid | 24.0B | 16 GB 15 GB + 0.2 GB cache | 8.1 GB in system RAM; Speed not estimated for this architecture |
| Mistral Small 3 Mistral AI | 23.6B | 16 GB 14 GB + 1.3 GB cache | 3.2–4.4 tokens/s Too slow for chat, 9.0 GB in system RAM |
| Cydonia 24B V4.1 Thedrummer | 23.6B | 16 GB 14 GB + 1.3 GB cache | 3.2–4.4 tokens/s Too slow for chat, 9.0 GB in system RAM |
| Cydonia 24B V4.1 Thedrummer | 23.6B | 16 GB 14 GB + 1.3 GB cache | 3.2–4.4 tokens/s Too slow for chat, 9.0 GB in system RAM |
| Safety GPT OSS 20B OpenAI | 21.5B 4.8B active | 14 GB 13 GB + 0.2 GB cache | 28–38 tokens/s Fast, 6.6 GB in system RAM |
| GPT OSS 20B OpenAI | 20.9B 4.2B active | 14 GB 13 GB + 0.2 GB cache | 30–41 tokens/s Fast, 6.3 GB in system RAM |
| Reka Flash 3 Rekaai | 20.9B | 15 GB 13 GB + 1.1 GB cache | 4.0–5.4 tokens/s Usable but slow, 7.2 GB in system RAM |
| Qwen3 14B Alibaba (Qwen) | 14.8B | 11 GB 9.0 GB + 1.3 GB cache | 7.1–9.7 tokens/s Usable but slow, 3.7 GB in system RAM |
| Phi 4 Microsoft | 14.7B | 11 GB 8.9 GB + 1.7 GB cache | 6.7–9.2 tokens/s Usable but slow, 4.0 GB in system RAM |
| Ministral 3 14B Mistral AI | 13.9B | 11 GB 8.5 GB + 1.3 GB cache | 7.9–11 tokens/s Usable but slow, 3.2 GB in system RAM |
| Gemma 3 12B IT Google DeepMind | 12.2B | 8.2 GB weights only | 0.8 GB in system RAM; Speed not estimated (architecture not public) |
| Llama Guard 4 12B Meta | 12.0B | 8.1 GB weights only | 0.7 GB in system RAM; Speed not estimated (architecture not public) |
| Granite 4.2 8B IBM | 8.8B | 7.5 GB 5.3 GB + 1.3 GB cache | 37–51 tokens/s Fast, 0.1 GB in system RAM |
85 larger models do not fit. Change the quantization, conversation length or system RAM in the tool.
Compared with similar cards
- NVIDIA GeForce RTX 3070 8 GB: same memory, so the same models fit; about the same speed.
- NVIDIA GeForce RTX 4060 8 GB: same memory, so the same models fit; about 38% slower on models that fit both (272 vs 448 GB/s).
- NVIDIA GeForce RTX 3080 10 GB: 10 GB, 22 models fit entirely (+3); about 62% faster on models that fit both (760 vs 448 GB/s).
Frequently asked questions
What is the largest AI model the NVIDIA GeForce RTX 5060 8 GB can run?
At 4-bit quantization with an 8K-token conversation, the largest model in our directory that fits entirely in its 8 GB of video memory is Qwen3.5 9B (6.9 GB). With 32 GB of dual-channel DDR5-5600 for the overflow, larger models such as Skyfall 36B V2 also run, more slowly, partly from system RAM.
Can the NVIDIA GeForce RTX 5060 8 GB run GPT OSS 20B?
Partly. GPT OSS 20B needs about 14 GB at 4-bit, so about 6.3 GB runs from system RAM (assuming 32 GB of dual-channel DDR5-5600) at an estimated 30 to 41 tokens per second.
Can the NVIDIA GeForce RTX 5060 8 GB run Qwen3 32B?
Partly. Qwen3 32B needs about 23 GB at 4-bit, so about 15 GB runs from system RAM (assuming 32 GB of dual-channel DDR5-5600) at an estimated 2.0 to 2.7 tokens per second.
Can the NVIDIA GeForce RTX 5060 8 GB run OpenAI GPT 120B?
No. OpenAI GPT 120B needs about 72 GB at 4-bit, more than the NVIDIA GeForce RTX 5060 8 GB can hold even with 32 GB of dual-channel DDR5-5600 for overflow.
These are estimates, not measurements: memory from each model's parameter count and published architecture, speed from memory bandwidth, calibrated on the AIPCs test bench. Drivers, software and prompt length move real results. How the estimate works.