Can the RTX 4090 run Ling 3.0 Tiny?
Yes. Ling 3.0 Tiny fits the RTX 4090's 24 GB at Q4_K_M (about 6.8 GB needed), running at an estimated 125 tok/s. There's room for up to FP16 if you want higher quality.
Every quantization
Ling 3.0 Tiny (7.9B) on 24 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 5 GB | 6.8 GB | Fits easily | ~125 tok/s |
| Q5_K_M | 6 GB | 7.8 GB | Fits easily | ~104 tok/s |
| Q8_0 | 8 GB | 9.8 GB | Fits easily | ~78 tok/s |
| FP16 | 16 GB | 17.8 GB | Fits | ~39 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 inclusionAI/Ling-3.0-tiny-GGUF -ngl 99Ollama pulls a Q4 build by default. Pick a larger quant only if the table above says it fits. Full Ling 3.0 Tiny details →
Compare
Same model, other hardware - and other models on this card
Ling 3.0 Tiny on other hardware
- RTX 5090~206 tok/s
- RTX 5090 D~205 tok/s
- RTX 6000D~180 tok/s
- RTX 3090~110 tok/s
- Radeon RX 7900 XTX~110 tok/s
- RTX 5080~110 tok/s
- RTX 3080 Ti~105 tok/s
- RTX 5080 Mobile~103 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 Ling 3.0 Tiny?
Yes. Ling 3.0 Tiny fits the RTX 4090's 24 GB at Q4_K_M (about 6.8 GB needed), running at an estimated 125 tok/s. There's room for up to FP16 if you want higher quality.
How much VRAM does Ling 3.0 Tiny need?
About 5 GB of weights at Q4_K_M, 8 GB at Q8_0 and 16 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is Ling 3.0 Tiny on the RTX 4090?
Roughly 125 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.