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

Can Qwen3.8 Flash Next run on the RTX 3060 12GB?

Not fully in VRAM. Even at 2-bit with 8K context, Qwen3.8 Flash Next needs about 76.4 GB, more than the 11.4 GB usable on the RTX 3060 12GB. It can still run with offload (slower): Q4_K_M with part of the model in system RAM, about 0.6–1.3 tokens/sec (estimate). Details and command.

Runs with offload (slower)

Runs with offload 4-bit (Q4_K_M) at 8K context: 4 of 48 layers on the RTX 3060 12GB (about 10.2 GB) and the other 44 in system RAM (about 102 GB). Needs a PC with at least 128 GB of system RAM. Estimated speed: 0.6–1.3 tokens/sec (very slow: fine for batch jobs, painful for chat), versus a bandwidth ceiling of ~9 tok/s if it fit fully in VRAM.

llama-server -hf bartowski/Qwen3.8-Flash-Next-GGUF:Q4_K_M -c 8192 -ngl 4 --no-mmproj

Estimate, not a benchmark. The command downloads the GGUF from Hugging Face. The speed range spans dual-channel DDR4-3200 to DDR5-6000 system RAM; your CPU, RAM speed and llama.cpp version move it. If llama.cpp runs out of GPU memory, lower -ngl by 2-3; if VRAM is left over, raise it for more speed. Recent llama.cpp builds can also pick the split automatically. How we estimate offload.

+ 0.8 GB with image input. The figures on this page are for text only. With image input enabled, the vision projector (mmproj) file loads alongside the model. llama.cpp's -hf downloads and loads it automatically unless you add --no-mmproj. Calculator with image input on.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •76.3 GB No76.4 GB No77.0 GB No79.2 GB No—
3-bit (Q3_K_M) •86.6 GB No86.7 GB No87.3 GB No89.5 GB No—
4-bit (Q4_K_M) •112 GB No112 GB No113 GB No115 GB No—
5-bit (Q5_K_M) •126 GB No126 GB No127 GB No129 GB No—
6-bit (Q6_K) •158 GB No158 GB No158 GB No160 GB No—
8-bit (Q8_0) •176 GB No176 GB No177 GB No179 GB No—
16-bit (F16/BF16) •331 GB No331 GB No331 GB No334 GB No—

• real GGUF file size from bartowski/Qwen3.8-Flash-Next-GGUF. Speed is a bandwidth ceiling (360 GB/s), not a benchmark. Methodology.

Hardware that does fit it

RTX PRO 6000 BlackwellDGX SparkRyzen AI Max+ 395 128GBMac M3 Max 128GBMac M4 Max 128GBH200

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

Qwen3.8 Flash Next on every GPU and Mac · Every model that runs on the RTX 3060 12GB · Other models that fit 12 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 (Qwen/Qwen3.8-Flash-Next), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.