Can I run this LLM?
Can a AMD Instinct MI300X (192GB) run GLM-5.3 Flash (MoE)?
GLM · MIT · estimated for a 192.0 GB machine at 4K context.
Yes — it runs great.
Best fit: GLM-5.3 Flash (MoE) at Q2_K · 125.7 GB · 220–329 tok/s on a AMD Instinct MI300X (192GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 125.7 GB | 220–329 tok/s | Runs great |
| Q3_K_M | 155.0 GB | 201–302 tok/s | Tight / slow |
| Q4_K_M | 200.8 GB | 178–266 tok/s | Won't fit |
| Q5_K_M | 243.7 GB | 160–240 tok/s | Won't fit |
| Q6_K | 281.0 GB | 147–221 tok/s | Won't fit |
| Q8_0 | 341.5 GB | 131–196 tok/s | Won't fit |
Open the full calculator →Everything a AMD Instinct MI300X (192GB) runsGLM-5.3 Flash (MoE) on other machinesWhat to buy to run it →
Ran GLM-5.3 Flash (MoE) on a AMD Instinct MI300X (192GB)? Add your real numbers →