Can Desktop PC · GeForce RTX 5070 · 32 GB RAM run Llama 3.3 70B Instruct?
12 GB VRAM + 32 GB RAM · 672 GB/s memory bandwidth · Llama 3.3 70B Instruct has 70.6B parameters.
Short answer
No. It doesn't fit in memory.
Needs ≈37 GB but only ≈35 GB of VRAM + system RAM is available after the OS and other apps.
Why it doesn’t fit
Even its smallest practical version (Q3_K_M) needs about 37 GB for the model, its context memory and the runtime. After Windows (≈4.5 GB), a browser with a few tabs (≈3.0 GB) and Open WebUI (≈1.0 GB), Desktop PC · GeForce RTX 5070 · 32 GB RAM has about 35 GB left, so it’s 2.4 GB short.
Ways to make it work
Close everything else
Not enough on its own: with every other app closed it’s still about 0.0 GB short.
Pick a smaller model from the same family
Get more memory
You’d want at least 45 GB of VRAM plus RAM in total. The machines below are the cheapest that run it comfortably.
Check your exact setup
These pages assume typical settings. A shorter context or a lighter chat app can change the answer.
Check Desktop PC · GeForce RTX 5070 · 32 GB RAM
The same applies to every workload we rate (chat, coding questions, coding in a repository, agentic coding and long documents): they all need at least as much memory as chat.
Other models for Desktop PC · GeForce RTX 5070 · 32 GB RAM
The best-rated models for chat on this machine.
- MiniCPM5 2B120–200 tok/sExcellent
- Qwen3.5 9B40–65 tok/sExcellent
- Qwen3.5 4B75–120 tok/sExcellent
- Gemma 4 12B40–65 tok/sExcellent
- GLM-4.6V-Flash (10B)40–65 tok/sExcellent
- Qwen3 8B45–75 tok/sExcellent
Cheapest machines for Llama 3.3 70B Instruct
Hardware rated comfortable or better for chat, lowest price first.
- Desktop PC · 2× GeForce RTX 3090 (48 GB) · 128 GB RAM$2,884 · 11–18 tok/sComfortable
- Mac Studio M5 Ultra 128 GB$5,499 · 10–16 tok/sComfortable
- Mac Studio M5 Ultra 256 GB$6,299 · 10–16 tok/sComfortable
- Mac Studio M5 Ultra 512 GB$7,099 · 10–16 tok/sComfortable
- Desktop PC · RTX PRO 6000 Blackwell · 128 GB RAM$17,284 · 17–25 tok/sExcellent
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.