Can RTX 3090 run Flint 40B-A2.5B?

Q: Can RTX 3090 run Flint 40B-A2.5B?

Yes. Measured 128.9 tok/s generation on RTX 3090, via llama.cpp 0.7.0-dev (build 11803), UD-Q3_K_XL. Source: https://llm-speed.com/r/r_v-sdiljpm7i The measured runs on it used UD-Q3_K_XL, not Q4_K_M. At Q4_K_M the weights are about 24.3 GB, more than 24 GB, so Q4_K_M doesn't fully fit without offloading part of the model to system RAM.

Yes. Measured 128.9 tok/s generation (llama.cpp 0.7.0-dev (build 11803), UD-Q3_K_XL; source).

Every measured result for Flint 40B-A2.5B on RTX 3090

Build	Quant / setup	Engine	tok/s
RTX 3090 (llm-speed signed run, Oct 2026): Flint 40B-A2.5B Q3_K_XL at 128.9 tok/s	UD-Q3_K_XL	llama.cpp 0.7.0-dev (build 11803)	128.9	source

Memory: RTX 3090 has 24 GB. Flint 40B-A2.5B weights are about 24.3 GB at Q4_K_M (39.8B params × 4.89 bits ÷ 8, before context/KV cache). Arithmetic, not a measurement; long contexts need more. Check other quants in the VRAM calculator. The measured runs on it used UD-Q3_K_XL, not Q4_K_M. At Q4_K_M the weights are about 24.3 GB, more than 24 GB, so Q4_K_M doesn't fully fit without offloading part of the model to system RAM.

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 Flint 40B-A2.5B: best home rig for Flint 40B-A2.5B.

Flint 40B-A2.5B on other hardware: Apple M4 Pro · RTX 4090

Other models measured on RTX 3090: DeepSeek R1 671B · GLM 4.7 Flash · Qwen3.6 27B · Qwen3.6 35B-A3B · Qwen3.8 27B · gpt-oss 20B

Not enough VRAM? Rent before you buy. Run Flint 40B-A2.5B 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.