Can the RTX 4070 run Ornith-1.5-9B?
Yes. Ornith-1.5-9B fits the RTX 4070's 12 GB at Q4_K_M (about 7.8 GB needed), running at an estimated 48 tok/s. There's room for up to Q8_0 if you want higher quality.
Every quantization
Ornith-1.5-9B (9.7B) on 12 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 6 GB | 7.8 GB | Fits | ~48 tok/s |
| Q5_K_M | 7 GB | 8.8 GB | Fits | ~41 tok/s |
| Q8_0 | 10 GB | 11.8 GB | Tight | ~29 tok/s |
| FP16 | 19 GB | 20.8 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 4070's 504 GB/s bandwidth (Estimated from memory bandwidth (llama.cpp decode)). Long contexts need more memory and run slower.
Run it
Copy, paste, go
llama-server -hf ornith-ai/Ornith-1.5-9B-GGUF -ngl 99Ollama pulls a Q4 build by default. Pick a larger quant only if the table above says it fits. Full Ornith-1.5-9B details →
Compare
Same model, other hardware - and other models on this card
Ornith-1.5-9B on other hardware
- RTX 5090~171 tok/s
- RTX 5090 D~171 tok/s
- RTX 6000D~150 tok/s
- RTX 4090~104 tok/s
- Radeon RX 7900 XTX~92 tok/s
- RTX 5080~92 tok/s
- RTX 3090~91 tok/s
- RTX 3080 Ti~87 tok/s
Also runs on the RTX 4070
- Qwen3 14B~36 tok/s
- Ornith-1.5-9B-OBLITERATED~48 tok/s
- Qwen3.5 9B~48 tok/s
- Llama 3.1 8B~53 tok/s
- Qwen3.5 4B~96 tok/s
- Qwen3-4B-Instruct-2507~145 tok/s
- Phi-4 Mini~116 tok/s
Frequently asked
Quick answers
Can the NVIDIA RTX 4070 run Ornith-1.5-9B?
Yes. Ornith-1.5-9B fits the RTX 4070's 12 GB at Q4_K_M (about 7.8 GB needed), running at an estimated 48 tok/s. There's room for up to Q8_0 if you want higher quality.
How much VRAM does Ornith-1.5-9B need?
About 6 GB of weights at Q4_K_M, 10 GB at Q8_0 and 19 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is Ornith-1.5-9B on the RTX 4070?
Roughly 48 tokens per second at Q4_K_M (single user, llama.cpp-style decode). This is an estimate from the RTX 4070's 504 GB/s memory bandwidth.