What AI can an RTX 3080 10GB run?

Quick verdict

PC with RTX 3080 10GB (10 GB) and 32 GB RAM can run 12 of the 31 models tracked here at a comfortable speed, and another 11 slowly. The largest chat or coding model that fits is Gemma 4 12B, which needs about 8.9 GB and generates roughly 43 words a second. The quickest is Gemma 4 E2B at about 171 words a second, which feels faster than you can read.

What limits this machine

Video memory (VRAM) is the limit: 10 GB on this card. A model must fit in VRAM to run fast. Anything larger spills into system RAM (32 GB in this setup), which works but is slow, because system RAM moves data at roughly 70 GB/s while the card moves 760 GB/s.

What it is good for

Chat and coding

Best chat pick: Gemma 4 12B at about 43 words a second. Best coding pick: Qwen2.5 Coder 7B at about 73.

Images

• Stable Diffusion XL: runs great, about about 11 s per image
• FLUX.2 klein 4B: slow, about about 38 s per image

Video

Video models need more memory than this machine has.

Voice and music

• Whisper large-v3 turbo: runs great, about about 42 s per 10 minutes of audio
• Kokoro TTS: runs great, about about 6 s per minute of speech
• Qwen3 TTS 1.7B: runs great, about about 30 s per minute of speech
• ACE-Step 1.5: slow, about about 3 min per 1 minute song

Fastest models here

• Gemma 4 E2B: about 171 words a second, faster than you can read
• Gemma 4 E4B: about 107 words a second, faster than you can read
• Qwen 3.5 4B: about 104 words a second, faster than you can read
• Qwen2.5 Coder 7B: about 73 words a second, faster than you can read
• DeepSeek R1 8B: about 66 words a second, faster than you can read

Memory headroom

Spare memory after loading the model decides how long a conversation or document can be before things slow down. With about 29 GB usable here:

• Gemma 4 12B needs 8.9 GB, leaving 19.8 GB spare, plenty for long documents.
• Gemma 4 E4B needs 7.4 GB, leaving 21.3 GB spare, plenty for long documents.
• Qwen 3.5 9B needs 7.4 GB, leaving 21.3 GB spare, plenty for long documents.
• Qwen3 VL 8B needs 6.9 GB, leaving 21.8 GB spare, plenty for long documents.
• DeepSeek R1 8B needs 6 GB, leaving 22.7 GB spare, plenty for long documents.

What does not fit, and by how much

• Llama 3.3 70B needs about 45.6 GB and this machine tops out near 29 GB, so it is about 17 GB short.
• gpt-oss 120B needs about 68.8 GB and this machine tops out near 29 GB, so it is about 40 GB short.
• Qwen 3.5 122B A10B needs about 85.5 GB and this machine tops out near 29 GB, so it is about 57 GB short.
• DeepSeek V3 671B needs about 424.7 GB and this machine tops out near 29 GB, so it is about 396 GB short.

How it compares

• PC with RTX 4060, RTX 3070, RTX 5060, RTX 4060 Laptop or RTX 4070 Laptop and 32 GB RAM: 3 fewer models; drops Gemma 4 12B, Stable Diffusion XL, Qwen3 TTS 1.7B.
• PC with RTX 3060 12GB (12 GB) and 32 GB RAM: 2 more models; adds Phi-4 14B, FLUX.2 klein 4B.
• PC with RTX 4070/4070 Super or RTX 5070 and 32 GB RAM: 2 more models; adds Phi-4 14B, FLUX.2 klein 4B.

Is an upgrade worth it?

The biggest single jump is Ryzen AI Max+ 395 (Strix Halo), 128 GB, which would unlock 15 more models, including gpt-oss 20B, Gemma 4 26B A4B, Qwen 3.5 35B A3B.

Questions