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

Can I run this LLM?

Can a AMD Instinct MI300X (192GB) run Qwen3.6 35B-A3B (MoE)?

Qwen · Apache 2.0 · estimated for a 192.0 GB machine at 4K context.

Yes — it runs great.

Runs great

Best fit: Qwen3.6 35B-A3B (MoE) at FP16 · 69.4 GB weights · 234–351 tok/s on a AMD Instinct MI300X (192GB).

Arena Text Overall · style-controlled

UnratedNo exact match

No reviewed exact Arena match

No reviewed exact model/configuration match in the Arena Text Overall style-controlled snapshot. No family or editorial score is substituted. 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
70.3 GB
Weights + KV cache + runtime overhead
Estimated generation
234–351 tok/s
Estimated first token
~0.1s

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.

Qwen3.6 35B-A3B (MoE) quantizations on AMD Instinct MI300X (192GB), estimated at 4K context. Weights and total memory are shown separately.
QuantWeightsTotal memorySpeedFit
Q2_K12.3 GB13.2 GB331–497 tok/sRuns great
Q3_K_M16.6 GB17.5 GB321–482 tok/sRuns great
Q4_K_M22.1 GB23.0 GB309–464 tok/sRuns great
Q5_K_M26.5 GB27.3 GB300–450 tok/sRuns great
Q6_K29.3 GB30.2 GB295–442 tok/sRuns great
Q8_036.9 GB37.8 GB281–421 tok/sRuns great
FP1669.4 GB70.3 GB234–351 tok/sRuns great
Open the full calculator →Everything a AMD Instinct MI300X (192GB) runsQwen3.6 35B-A3B (MoE) on other machinesWhat to buy to run it →

Ran Qwen3.6 35B-A3B (MoE) on a AMD Instinct MI300X (192GB)? Add your real numbers →