RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can Llama 3.1 70B run on the A100 40GB?

Yes. At 8K context the best fit is Q2_K, using about 27.7 GB of the 38.0 GB usable on the A100 40GB. Estimated speed ceiling: ~59 tokens/sec.

Better quality with offload: 4-bit (Q4_K_M)

Runs with offload 4-bit (Q4_K_M) at 8K context: 70 of 80 layers on the A100 40GB (about 37.5 GB) and the other 10 in system RAM (about 5.3 GB). Needs a PC with at least 32 GB of system RAM. Estimated speed: 3.8–6.9 tokens/sec (slow but usable), versus a bandwidth ceiling of ~37 tok/s if it fit fully in VRAM.

llama-server -hf mradermacher/Meta-Llama-3.1-70B-i1-GGUF:Q4_K_M -c 8192 -ngl 70

Estimate, not a benchmark. The command downloads the GGUF from Hugging Face. The speed range spans dual-channel DDR4-3200 to DDR5-6000 system RAM; your CPU, RAM speed and llama.cpp version move it. If llama.cpp runs out of GPU memory, lower -ngl by 2-3; if VRAM is left over, raise it for more speed. Recent llama.cpp builds can also pick the split automatically. How we estimate offload.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •26.5 GB Fits27.7 GB Fits35.2 GB Tight65.2 GB No59
3-bit (Q3_K_M) •33.8 GB Fits35.1 GB Tight42.6 GB No72.6 GB No45
4-bit (Q4_K_M) •41.5 GB No42.7 GB No50.2 GB No80.2 GB No—
5-bit (Q5_K_M) •48.4 GB No49.7 GB No57.2 GB No87.2 GB No—
6-bit (Q6_K)55.8 GB No57.0 GB No64.5 GB No94.5 GB No—
8-bit (Q8_0)71.7 GB No73.0 GB No80.5 GB No110 GB No—
16-bit (F16/BF16)133 GB No135 GB No142 GB No172 GB No—

• real GGUF file size from mradermacher/Meta-Llama-3.1-70B-i1-GGUF. Speed is a bandwidth ceiling (1555 GB/s), not a benchmark. Methodology.

What fits instead

"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.

More

Llama 3.1 70B on every GPU and Mac · Every model that runs on the A100 40GB · Other models that fit 48 GB VRAM · Try other settings in the calculator

Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs

Data: Hugging Face Hub (meta-llama/Llama-3.1-70B), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.