Can RTX 5090 run Ornith 1.5 35B-A3B?

Q: Can RTX 5090 run Ornith 1.5 35B-A3B?

Yes. Measured 273.2 tok/s generation on RTX 5090, via llama-server b10448, no MTP, Q4_K_M, f16 KV. Source: https://kgptalkie.com/tutorials/llm-benchmarking/qwen-3-8-27b-llama-cpp-speed-settings

Yes. Measured 273.2 tok/s generation (llama-server b10448, no MTP, Q4_K_M, f16 KV; source).

Every measured result for Ornith 1.5 35B-A3B on RTX 5090

Build	Quant / setup	Engine	tok/s
RTX 5090 on Windows 11: Ornith 1.5 35B-A3B at 273 tok/s, Gemma 4 26B-A4B at 232, Qwen3.8 27B 73.6 (137 with MTP)	Q4_K_M, f16 KV	llama-server b10448, no MTP	273.2	source

Memory: RTX 5090 has 32 GB. Ornith 1.5 35B-A3B weights are about 22.0 GB at Q4_K_M (35.95B params × 4.89 bits ÷ 8, before context/KV cache). Arithmetic, not a measurement; long contexts need more. Check other quants in the VRAM calculator.

Speeds are decode (generation) tokens/sec as reported by each source; quant, engine and context differ, so small gaps are noise.

All measured speeds for Ornith 1.5 35B-A3B: best home rig for Ornith 1.5 35B-A3B.

Ornith 1.5 35B-A3B on other hardware: Intel Arc Pro B70

Other models measured on RTX 5090: DeepSeek V4.1 Flash · Flint 40B-A2.5B · GLM-5.3 Flash · Gemma 4 12B · Gemma 4 26B-A4B · Gemma 4 31B · Nemotron 3.5 Bolt 74B-A9B · Ornith 1.5 122B · Qwen3.5 9B · Qwen3.6 27B · Qwen3.6 35B-A3B · Qwen3.8 27B · Qwen3.8 Flash-Next · gpt-oss 20B

Not enough VRAM? Rent before you buy. Run Ornith 1.5 35B-A3B on a bigger GPU on a rented 24–96 GB cloud GPU by the hour and see the real speed before spending €1,000+. Try it on Runpod
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.