Can the RTX 3080 Ti run Granite 4.2 8B?
Yes. Granite 4.2 8B fits the RTX 3080 Ti's 12 GB at Q4_K_M (about 6.8 GB needed), running at an estimated 105 tok/s. There's room for up to Q8_0 if you want higher quality.
Every quantization
Granite 4.2 8B (8.8B) on 12 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 5 GB | 6.8 GB | Fits easily | ~105 tok/s |
| Q5_K_M | 6 GB | 7.8 GB | Fits | ~87 tok/s |
| Q8_0 | 9 GB | 10.8 GB | Tight | ~58 tok/s |
| FP16 | 18 GB | 19.8 GB | Too big | - |
Estimates. Needs = weights + 1.8 GB for KV cache and runtime at modest context. Speed is single-stream decode scaled from the RTX 3080 Ti's 912 GB/s bandwidth (XiongjieDai/GPU-Benchmarks-on-LLM-Inference). Long contexts need more memory and run slower.
Run it
Copy, paste, go
llama-server -hf ibm-granite/granite-4.2-8b-GGUF -ngl 99Ollama pulls a Q4 build by default. Pick a larger quant only if the table above says it fits. Full Granite 4.2 8B details →
Compare
Same model, other hardware - and other models on this card
Granite 4.2 8B on other hardware
- RTX 5090~206 tok/s
- RTX 5090 D~205 tok/s
- RTX 6000D~180 tok/s
- RTX 4090~125 tok/s
- RTX 3090~110 tok/s
- Radeon RX 7900 XTX~110 tok/s
- RTX 5080~110 tok/s
- RTX 5080 Mobile~103 tok/s
Also runs on the RTX 3080 Ti
- Qwen3 14B~65 tok/s
- Gemma 4 12B~75 tok/s
- Qwen3.5 9B~87 tok/s
- Llama 3.1 8B~95 tok/s
- Ling 3.0 Tiny~105 tok/s
- Mistral-7B-Instruct-v0.2~131 tok/s
- Qwen3.5 4B~174 tok/s
- Qwen3-4B-Instruct-2507~261 tok/s
Frequently asked
Quick answers
Can the NVIDIA RTX 3080 Ti run Granite 4.2 8B?
Yes. Granite 4.2 8B fits the RTX 3080 Ti's 12 GB at Q4_K_M (about 6.8 GB needed), running at an estimated 105 tok/s. There's room for up to Q8_0 if you want higher quality.
How much VRAM does Granite 4.2 8B need?
About 5 GB of weights at Q4_K_M, 9 GB at Q8_0 and 18 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is Granite 4.2 8B on the RTX 3080 Ti?
Roughly 105 tokens per second at Q4_K_M (single user, llama.cpp-style decode). This is an estimate from the RTX 3080 Ti's 912 GB/s memory bandwidth.