What can you run on a 16GB graphics card?

With 16GB VRAM you can run 9 of the 30 open-source models we track — up to about 22B parameters at Q4 quantization. The most popular that fits is Qwen3.5-9B, needing 6.8 GB and generating around ~82 tok/s on typical hardware of this size.

Typical machines: RTX 4080 · RTX 5080 · RTX 4060 Ti 16GB · RX 7800 XT · Arc A770. After the operating system takes its share, about 16 GB is free for a model.

Having the memory is not the same as having the speed

16GB VRAM decides whether a model loads. How fast it answers is decided by memory bandwidth — how quickly your machine can read the model, which it must do once for every word it writes. Machines with 16GB VRAM span 288–960 GB/s, so the fastest is about 3.3× quicker than the slowest with identical capacity. The table quotes a RTX 4080; pick yours below to see the difference. Why bandwidth and not the processor →

288 GB/sGeForce RTX 4060 Ti (16GB)· NVIDIA published specification: 288 GB/s GDDR6, 128-bit
560 GB/sIntel Arc A770 (16GB)· Intel published specification: 560 GB/s GDDR6, 256-bit
624 GB/sRadeon RX 7800 XT (16GB)· AMD published specification: 624 GB/s GDDR6, 256-bit
717 GB/sGeForce RTX 4080 (16GB)· NVIDIA published specification: 716.8 GB/s GDDR6X, 256-bit
960 GB/sGeForce RTX 5080 (16GB)· NVIDIA published specification: 960 GB/s GDDR7, 256-bit

Models that run on 16GB VRAM in 2026

ModelSizeMemoryEst. speedFeels like
Qwen3.5-9BAlibaba / Qwen9.7B6.8 GBRuns well~82 tok/sFast
gpt-oss-20bOpenAI · MoE22B13 GBRuns well~200 tok/s4.3B activeFast
Qwen3.5-4BAlibaba / Qwen4.7B3.8 GBRuns well~170 tok/sFast
Qwen3.5-0.8BAlibaba / Qwen873M1.3 GBRuns well~875 tok/sFast
Qwen3.5-2BAlibaba / Qwen2.3B2.0 GBRuns well~364 tok/sFast
Olmo-3-7B-InstructAi27.3B7.2 GBRuns well~104 tok/sFast
GLM-4.6V-FlashZhipu AI10B7.0 GBRuns well~76 tok/sFast
ERNIE-4.5-21B-A3B-PTBaidu AI · MoE22B15 GBTight~35 tok/sFast
ERNIE-4.5-0.3B-PTBaidu AI361M853 MBRuns well~1937 tok/sFast

All figures at Q4_K_M quantization, 4K context. “Memory” includes the model, its context cache and runtime overhead. Speed is calculated, not benchmarked: 717 GB/s × 0.65 ÷ bytes read per token, assuming a RTX 4080. Scale it by your own machine's bandwidth from the list above. Mixture-of-experts models read only their active parameters per token, which is why some large ones outrun smaller dense models.

Image generators that also fit

These make pictures rather than text. Their memory use scales with the resolution you generate at, not conversation length, so treat these figures as a floor rather than a ceiling.

What you'd need more memory for

The next models up, and what they ask for.

See what 24GB gets you →

Other hardware

Verified against HuggingFace on 2026-08-01New to this? Start here →Runs on a laptop and up · last 12 months only