← All GPUs

RTX 3080

10GB VRAM  ·  Ampere (CUDA)

Quick answer: The fastest listed local LLM on RTX 3080 is llama3.2-3b at 95 tok/s decode, with 9 Q4_K_M models marked as fitting this hardware.
ℹ️ VRAM estimates assume GGUF format and 2048-token context. Running at 8k+ context adds 2–4GB. Tokens/sec = generation (decode) speed only. 6 rows currently link to community benchmark sources.
Model Quant VRAM Tok/s Data Fits
llama3.2-3b Q4_K_M 2GB 95 Community benchmark ✓
gemma3-4b Q4_K_M 3GB 88 Community benchmark ✓
mistral-7b Q4_K_M 4.7GB 67 Community benchmark ✓
qwen2.5-7b Q4_K_M 4.7GB 65 Community benchmark ✓
llama3.1-8b Q4_K_M 5GB 62 Community benchmark ✓
deepseek-r1-7b Q4_K_M 4.7GB 60 estimate ✓
gemma3-12b Q4_K_M 7.5GB 38 Community benchmark ✓
qwen2.5-14b Q4_K_M 9GB 28 estimate Tight
phi-4-14b Q4_K_M 9GB 26 estimate Tight
gemma3-27b Q4_K_M 16.5GB — estimate ✗ No
llama3.1-70b Q4_K_M 42GB — estimate ✗ No
mistral-24b Q4_K_M 14.4GB — estimate ✗ No
nemotron-51b Q4_K_M 30.6GB — estimate ✗ No
qwen2.5-32b Q4_K_M 19.5GB — estimate ✗ No
qwen2.5-72b Q4_K_M 43.5GB — estimate ✗ No
Improve this GPU page
Have a RTX 3080 benchmark run?

Add model, quantization, context length, and decode tok/s so this page can answer more long-tail local LLM searches accurately.

Contribute RTX 3080 data

You might also compare

gemma3-4b vs llama3.2-3b on RTX 3080
GPU-specific speed and VRAM fit
llama3.2-3b vs mistral-7b on RTX 3080
GPU-specific speed and VRAM fit
llama3.1-8b vs mistral-7b
Quality and model-level tradeoffs
phi-4-14b vs qwen2.5-14b
Quality and model-level tradeoffs

RTX 3080 local LLM FAQ

What LLMs can run on RTX 3080?

9 Q4_K_M models in this dataset are marked as fitting on RTX 3080. Start with the table rows marked as fitting, then compare VRAM and decode tok/s.

What is the fastest local LLM on RTX 3080?

llama3.2-3b is the fastest listed model on RTX 3080 at 95 decode tokens per second.

How much VRAM does RTX 3080 have for local LLMs?

RTX 3080 has 10GB VRAM. Models near 80% or more of that capacity are marked as tight fits.

Can RTX 3080 run 70B local LLMs?

RTX 3080 is not marked as fitting the listed 70B-class Q4_K_M models in this dataset. Check the fit column before trying larger context windows.

What quantization should I use on RTX 3080?

Use Q4_K_M as the baseline for this site. It is the comparison format used across the current benchmark table and keeps VRAM requirements predictable.

Last updated: 2026-06-11 · Source · Improve this data