Skip to content

Can My GPU or Mac Run This LLM?

The naive estimate — “7 billion parameters at 4 bits is 4 GB, it fits” — breaks on long context, where the KV cache can outweigh the model itself. This one counts it.

No signup, no email

On RTX 3090 24GB at 8K context, 8 of 12 listed models fit in memory.

ModelParametersBest quantization that fitsMemory neededVerdict
Qwen3 4BAlibaba4BFP169.5 GBweights 7.5 GB + KV cache 1.1 GB + overhead 1.0 GBfits
Gemma 3 4BGoogle4.3BFP1610.1 GBweights 8.0 GB + KV cache 1.1 GB + overhead 1.0 GBfits
Llama 3.1 8BMeta8BFP1617.2 GBweights 14.9 GB + KV cache 1.0 GB + overhead 1.3 GBfits
Qwen3 8BAlibaba8.2BFP1617.8 GBweights 15.3 GB + KV cache 1.1 GB + overhead 1.4 GBfits
Gemma 3 12BGoogle12.2BQ815.5 GBweights 11.4 GB + KV cache 3.0 GB + overhead 1.2 GBfits
Mistral Small 3.2 24BMistral AI24BQ5_K_M18.3 GBweights 15.6 GB + KV cache 1.3 GB + overhead 1.4 GBfits
Gemma 3 27BGoogle27.4BQ4_K_M19.7 GBweights 14.5 GB + KV cache 3.9 GB + overhead 1.3 GBfits
Qwen3 32BAlibaba32.8B20.9 GBweights 17.4 GB + KV cache 2.0 GB + overhead 1.5 GBtight
Qwen3 30B-A3B (MoE)Alibaba30.5B3.3B activeQ4_K_M18.4 GBweights 16.2 GB + KV cache 0.8 GB + overhead 1.4 GBfits
Llama 3.3 70BMeta70.6B42.5 GBweights 37.5 GB + KV cache 2.5 GB + overhead 2.5 GBdoes not fit
Qwen3 235B-A22B (MoE)Alibaba235B22B active133.1 GBweights 124.8 GB + KV cache 1.5 GB + overhead 6.8 GBdoes not fit
DeepSeek V3 671B (MoE)DeepSeek671B37B active405.1 GBweights 356.2 GB + KV cache 30.5 GB + overhead 18.4 GBdoes not fit

Pricing verified 2026-08-12

How this is calculated

Memory = weights (parameters × bytes per parameter at the chosen quantization) + KV cache (2 × layers × KV heads × head dimension × context tokens × 2 bytes) + overhead for buffers and the runtime. “Tight” means over 85% utilisation — technically it fits, but the first longer request will likely run out of memory. We make no claim about speed: that depends on the runtime, the quantization and memory bandwidth.

Now the harder question

Counting tokens is the easy part. The hard part is deciding which processes in your company should go to AI agents, and in what order. That is what our AI-role org chart is for.

FAQ

What is quantization, and how much quality does it cost?
Quantization lowers the precision of the weights: 8, 6, 5 or 4 bits per parameter instead of 16. Q8 is nearly indistinguishable from the original, Q5 and Q6 lose a little, and Q4 degrades noticeably on hard tasks — but it fits a model twice the size.
Why is less memory available than my Mac has installed?
Mac memory is shared between the system and the GPU. macOS and your apps always hold part of it, so we count roughly two thirds on machines up to 24 GB and three quarters above that.
If a model does not fit, will it refuse to run?
It will run, but some layers spill to system RAM or disk and throughput drops several-fold. That is usually unacceptable for chat, and sometimes acceptable for overnight batch work.

en

Can My GPU Run This LLM? — VRAM calculator for local models | AI Advisory Board