Rent a GPU

Can the NVIDIA RTX 3090 Ti run Granite 3.3 8B?

RTX 3090 Ti × Granite 3.3 8B8K context
YesRuns fully on the GPU
Memory at FP1618.3 GB of 24 GB
Weights 16.3 GBKV cache 1.3 GBRuntime 0.6 GB
QuantFP16Full quality
Speed~37tokens per second
Max context41Ktokens that fit at FP16
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Yes. The NVIDIA RTX 3090 Ti can run Granite 3.3 8B fully in VRAM at FP16 (full quality), using about 18.3 GB of the 24 GB available, at roughly 37 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Granite 3.3 8B:

ollama run granite3.3:8b

Ollama's default download is Q4_K_M (about 6.9 GB here). You have room for FP16, which is full quality: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the RTX 3090 Ti

Run it in the cloud

No NVIDIA RTX 3090 Ti? Run Granite 3.3 8B in the cloud.

Rent a cloud GPU by the hour. No upfront cost, stop any time.

Rent a GPU on RunPodRent a GPU on Vast.ai

Memory needed by quantization

At 8,192 tokens of context. The black line marks the 24 GB the NVIDIA RTX 3090 Ti can use.

QuantQualityMemoryFits?Speed
FP16Full quality18.3 GBFits~37 tok/s
Q8_0Near-lossless10.6 GBFits~70 tok/s
Q6_KExcellent8.6 GBFits~90 tok/s
Q5_K_MVery good7.8 GBFits~104 tok/s
Q4_K_MGood, most popular6.9 GBFits~122 tok/s
Q3_K_MNoticeably degraded5.9 GBFits~151 tok/s
Q2_KHeavily degraded5 GBFits~197 tok/s

Measured speed from real RTX 3090 Ti owners

Tokens per second that people measured on their own NVIDIA RTX 3090 Ti, next to our estimate.

No one has measured Granite 3.3 8B on the NVIDIA RTX 3090 Ti yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an RTX 3090 Ti? Add your real speed

One command times Granite 3.3 8B in your own Ollama, shows you exactly what it would send, and asks before sending anything. No sign-up, no personal data.

macOS and Linux

curl -fsSL https://gpufit.dev/bench.sh | sh -s -- granite3.3:8b

Windows (PowerShell)

$env:GPUFIT_MODEL="granite3.3:8b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Granite 3.3 8B comfortably

Models that run well on the NVIDIA RTX 3090 Ti

Frequently asked questions

Can NVIDIA RTX 3090 Ti run Granite 3.3 8B?

Yes. The NVIDIA RTX 3090 Ti can run Granite 3.3 8B fully in VRAM at FP16 (full quality), using about 18.3 GB of the 24 GB available, at roughly 37 tokens/second.

How much VRAM does Granite 3.3 8B need?

About 6.9 GB at Q4_K_M with 8,192 tokens of context, and about 18.3 GB at full FP16 precision.

How fast is Granite 3.3 8B on the NVIDIA RTX 3090 Ti?

Roughly 37 tokens per second at FP16, estimated from the NVIDIA RTX 3090 Ti's 1008 GB/s memory bandwidth.