Skip to content
can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI355X (288GB) run GLM-5.3 (MoE)?

GLM · See model card · estimated for a 288.0 GB machine at 4K context.

Yes, but it's tight.

Tight / slow

Best fit: GLM-5.3 (MoE) at Q2_K · 253.9 GB weights · 197–295 tok/s on a AMD Instinct MI355X (288GB).

Arena Text Overall · style-controlled

UnratedAmbiguous match

Ambiguous Arena identity; unrated

Arena identity is ambiguous. The published Max configuration is not automatically the generic GLM 5.3 release. No rating is assigned or used for ranking. Local quantization quality is unmeasured.

Snapshot published 2026-10-08 · snapshot imported 2026-10-11 UTC · validated last-good data · manual refresh

Arena leaderboard dataset · Arena / lmarena-ai, Arena Leaderboard Dataset (CC BY 4.0). Selected Text Overall style-controlled rows; field names adapted, ratings unchanged. · dataset CC BY 4.0 · revision e16f90232986

Total memory at 4K context
255.1 GB
Weights + KV cache + runtime overhead
Estimated generation
197–295 tok/s
Estimated first token
~1.0s

Every quantization on this machine

On small screens, each quant lists every metric below its name. On wider screens, scroll sideways for total memory, speed and fit. Keyboard: focus the table, then use the arrow keys. Quant names stay visible.

GLM-5.3 (MoE) quantizations on AMD Instinct MI355X (288GB), estimated at 4K context. Weights and total memory are shown separately.
QuantWeightsTotal memorySpeedFit
Q2_K253.9 GB255.1 GB197–295 tok/sTight / slow
Q3_K_M343.0 GB344.2 GB— not residentWon't fit
Q4_K_M467.3 GB468.5 GB— not residentWon't fit
Q5_K_M562.5 GB563.7 GB— not residentWon't fit
Q6_K684.4 GB685.6 GB— not residentWon't fit
Q8_0801.4 GB802.6 GB— not residentWon't fit
FP161508.0 GB1509.2 GB— not residentWon't fit
Open the full calculator →Everything a AMD Instinct MI355X (288GB) runsGLM-5.3 (MoE) on other machinesWhat to buy to run it →

Ran GLM-5.3 (MoE) on a AMD Instinct MI355X (288GB)? Add your real numbers →