RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?API pricesVRAM calculatorNew

Can Kimi VL A3B Thinking 2506 run on the L40S?

Yes. At 8K context the best fit is Q8_0, using about 16.8 GB of the 45.6 GB usable on the L40S. Estimated speed ceiling: ~278 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)6.6 GB Fits6.7 GB Fits7.4 GB Fits10.2 GB Fits768
3-bit (Q3_K_M)8.3 GB Fits8.4 GB Fits9.1 GB Fits12.0 GB Fits589
4-bit (Q4_K_M) •10.6 GB Fits10.8 GB Fits11.5 GB Fits14.3 GB Fits448
5-bit (Q5_K_M)11.7 GB Fits11.8 GB Fits12.5 GB Fits15.4 GB Fits404
6-bit (Q6_K)13.4 GB Fits13.5 GB Fits14.2 GB Fits17.0 GB Fits351
8-bit (Q8_0) •16.6 GB Fits16.8 GB Fits17.5 GB Fits20.3 GB Fits278
16-bit (F16/BF16) •60.3 GB No60.4 GB No61.1 GB No64.0 GB No—

• real GGUF file size from ggml-org/Kimi-VL-A3B-Thinking-2506-GGUF. Speed is a bandwidth ceiling (864 GB/s), not a benchmark. Methodology.

What fits instead

"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.

More

Kimi VL A3B Thinking 2506 on every GPU and Mac · Every model that runs on the L40S · Other models that fit 48 GB VRAM · Try other settings in the calculator

Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs

Data: Hugging Face Hub (moonshotai/Kimi-VL-A3B-Thinking-2506), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.