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

Can GLM 5.3 Flash run on the Arc A770 16GB?

Not fully in VRAM. Even at 2-bit with 8K context, GLM 5.3 Flash needs about 113 GB, more than the 15.2 GB usable on the Arc A770 16GB. It can still run with offload (slower): Q2_K with part of the model in system RAM, about 7.3–14 tokens/sec (estimate). Details and command.

Runs with offload (slower)

Runs with offload 2-bit (Q2_K) at 8K context: all attention layers plus the experts of 4 of 43 MoE layers on the Arc A770 16GB (about 13.6 GB), and the experts of the other 39 layers in system RAM (about 98.7 GB). Needs a PC with at least 128 GB of system RAM. Estimated speed: 7.3–14 tokens/sec (slow but usable), versus a bandwidth ceiling of ~81 tok/s if it fit fully in VRAM.

llama-server -m glm-5-3-flash-Q2_K.gguf -c 8192 -ngl 999 --n-cpu-moe 41

Estimate, not a benchmark. The GGUF repo we found (unsloth/GLM-5.3-Flash-GGUF) has no Q2_K file; point -m at your own Q2_K GGUF. 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, raise --n-cpu-moe by 1-2; if VRAM is left over, lower it for more speed. Recent llama.cpp builds can also pick the split automatically. How we estimate offload.

+ 1.1 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)113 GB No113 GB No113 GB No115 GB No—
3-bit (Q3_K_M)147 GB No147 GB No147 GB No149 GB No—
4-bit (Q4_K_M)184 GB No184 GB No184 GB No185 GB No—
5-bit (Q5_K_M)214 GB No214 GB No214 GB No216 GB No—
6-bit (Q6_K)246 GB No246 GB No247 GB No248 GB No—
8-bit (Q8_0) •318 GB No318 GB No319 GB No320 GB No—
16-bit (F16/BF16) •598 GB No598 GB No599 GB No600 GB No—

• real GGUF file size from unsloth/GLM-5.3-Flash-GGUF. Speed is a bandwidth ceiling (560 GB/s), not a benchmark. Methodology.

Hardware that does fit it

H200Mac M2 Ultra 192GBMac M3 Ultra 256GBMac M3 Ultra 512GB

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

GLM 5.3 Flash on every GPU and Mac · Every model that runs on the Arc A770 16GB · Other models that fit 16 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 (zai-org/GLM-5.3-Flash), Intel specs. Model data last checked 2026-11-18; refreshed hourly.