Can I run this LLM?
Can a AMD Instinct MI300X (192GB) run Kimi Linear 48B-A3B (MoE)?
Kimi · MIT · estimated for a 192.0 GB machine at 4K context.
Yes — it runs great.
Runs greatBest fit: Kimi Linear 48B-A3B (MoE) at FP16 · 98.3 GB weights · 234–352 tok/s on a AMD Instinct MI300X (192GB).
Arena Text Overall · style-controlled
UnratedNo exact matchNo 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
- 99.1 GB
- Weights + KV cache + runtime overhead
- Estimated generation
- 234–352 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.
| Quant | Weights | Total memory | Speed | Fit |
|---|---|---|---|---|
| Q2_K | 17.5 GB | 18.4 GB | 333–499 tok/s | Runs great |
| Q3_K_M | 22.7 GB | 23.5 GB | 324–486 tok/s | Runs great |
| Q4_K_M | 30.1 GB | 30.9 GB | 312–468 tok/s | Runs great |
| Q5_K_M | 35.1 GB | 35.9 GB | 305–457 tok/s | Runs great |
| Q6_K | 40.5 GB | 41.3 GB | 297–446 tok/s | Runs great |
| Q8_0 | 52.3 GB | 53.1 GB | 282–423 tok/s | Runs great |
| FP16 | 98.3 GB | 99.1 GB | 234–352 tok/s | Runs great |
Ran Kimi Linear 48B-A3B (MoE) on a AMD Instinct MI300X (192GB)? Add your real numbers →