Can the RTX 4090 run Granite 4.2 3B?
Yes. Granite 4.2 3B fits the RTX 4090's 24 GB at Q4_K_M (about 3.8 GB needed), running at an estimated 313 tok/s. There's room for up to FP16 if you want higher quality.
Every quantization
Granite 4.2 3B (3.7B) on 24 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 2 GB | 3.8 GB | Fits easily | ~313 tok/s |
| Q5_K_M | 3 GB | 4.8 GB | Fits easily | ~209 tok/s |
| Q8_0 | 4 GB | 5.8 GB | Fits easily | ~156 tok/s |
| FP16 | 7 GB | 8.8 GB | Fits easily | ~89 tok/s |
Estimates. Needs = weights + 1.8 GB for KV cache and runtime at modest context. Speed is single-stream decode scaled from the RTX 4090's 1008 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-4.2-3b-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 3B details →
Compare
Same model, other hardware - and other models on this card
Granite 4.2 3B on other hardware
- RTX 5090~514 tok/s
- RTX 5090 D~513 tok/s
- RTX 6000D~450 tok/s
- Radeon RX 7900 XTX~275 tok/s
- RTX 5080~275 tok/s
- RTX 3090~274 tok/s
- RTX 3080 Ti~261 tok/s
- RTX 5080 Mobile~257 tok/s
Also runs on the RTX 4090
- Qwen3-Coder-30B-A3B-Instruct~236 tok/s
- Qwen3-30B-A3B-Instruct-2507~236 tok/s
- Qwen3.6 27B~39 tok/s
- Qwen3.8 27B~39 tok/s
- Gemma 4 26B A4B~184 tok/s
- gpt-oss-20b~208 tok/s
- Nemotron 3.5 Lightning~63 tok/s
- Qwen2.5-Coder-14B-Instruct~70 tok/s
Frequently asked
Quick answers
Can the NVIDIA RTX 4090 run Granite 4.2 3B?
Yes. Granite 4.2 3B fits the RTX 4090's 24 GB at Q4_K_M (about 3.8 GB needed), running at an estimated 313 tok/s. There's room for up to FP16 if you want higher quality.
How much VRAM does Granite 4.2 3B need?
About 2 GB of weights at Q4_K_M, 4 GB at Q8_0 and 7 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is Granite 4.2 3B on the RTX 4090?
Roughly 313 tokens per second at Q4_K_M (single user, llama.cpp-style decode). This is an estimate from the RTX 4090's 1008 GB/s memory bandwidth.