Can I run this LLM?
Can a AMD Instinct MI300X (192GB) run Llama 3.2 1B?
Llama · Llama 3.2 Community · estimated for a 192.0 GB machine at 4K context.
Yes — it runs great.
Runs greatBest fit: Llama 3.2 1B at FP16 · 2.5 GB weights · 295–442 tok/s on a AMD Instinct MI300X (192GB).
Arena Text Overall · style-controlled
1,111FP16 untestedllama-3.2-1b-instruct · published configuration reference · FP16 not tested
Arena Text Overall (style-controlled), exact published entry llama-3.2-1b-instruct, 2026-10-08: reference rating 1,111.1. Published confidence bounds 1,103.2–1,119. 8,045 votes. Published llama-3.2-1b-instruct configuration reference. Reasoning mode is not disclosed by the Arena dataset. Tested precision, runtime and sampling settings are not disclosed in this dataset. Selected FP16 has not been measured by this Arena entry. No quantization quality adjustment is applied.
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
- 3.4 GB
- Weights + KV cache + runtime overhead
- Estimated generation
- 295–442 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 |
|---|---|---|---|---|
| Q4_K_M | 0.8 GB | 1.7 GB | 337–506 tok/s | Runs great |
| Q5_K_M | 0.9 GB | 1.8 GB | 334–501 tok/s | Runs great |
| Q6_K | 1.0 GB | 2.0 GB | 331–497 tok/s | Runs great |
| Q8_0 | 1.3 GB | 2.3 GB | 323–484 tok/s | Runs great |
| FP16 | 2.5 GB | 3.4 GB | 295–442 tok/s | Runs great |
Ran Llama 3.2 1B on a AMD Instinct MI300X (192GB)? Add your real numbers →