AMD Instinct MI300X 192GB vs AMD Strix Halo 128GB for local LLMs
3 reports on the AMD Instinct MI300X 192GB and 318 on the AMD Strix Halo 128GB
Which is faster for local LLMs?
On Qwen3-Coder 30B · 3B active at 16-bit, the AMD Instinct MI300X 192GB has 184.5 generation tokens/s (2 runs); the AMD Strix Halo 128GB has 9.2 generation tokens/s (one run); prompt processing 154.0 tokens/s (one run). Those are community reports whose engines and settings differ, so the gap is a rough sign, not a controlled measure of the two cards. Memory bandwidth, which caps how fast a card can write, is 20.7x higher on the AMD Instinct MI300X 192GB (5,300 GB/s on the AMD Instinct MI300X 192GB, 256 on the AMD Strix Halo 128GB).
- Memory
- 192GB
- Memory bandwidth
- 5,300 GB/s
- FP16 compute
- 1307 TFLOPS
- Reports
- 3
- Memory
- 128GB unified
- Memory bandwidth
- 256 GB/s
- FP16 compute
- 59 TFLOPS
- Reports
- 318
Measured on both
Generation and prompt processing speeds from plain runs (one device, one request, no speculative decoding, the whole model in the device's memory) of the same model size at the same bit class. Each side shows the engines and reported context behind its median. Context can mean a configured window or prompt depth, so these are community comparisons with differing settings. How to read these
| Model | AMD Instinct MI300X 192GB | AMD Strix Halo 128GB |
|---|---|---|
| Qwen3-Coder 30B · 3B active16-bit | 184.52 runsSGLang, vLLM128K context, 1 not stated | 9.2one runPP 154.0 (one run)engine not statedcontext not stated |
Estimated by the calculator
The quant the calculator recommends for each card and its estimated speed at a 32,768-token context with 32 GB of system RAM, from memory bandwidth and the model's shape. Where a model was also measured above, the measurement wins.
| Model | AMD Instinct MI300X 192GB | AMD Strix Halo 128GB |
|---|---|---|
| Qwen3-Coder 30B · 3B active | 194.3 t/sFP16 | 12.6 t/sFP16 |
| Qwen3.8 27B | 54.0 t/sFP16 | 3.5 t/sFP16 |
| Qwen3.8 125B · 6B active | 184.6 t/sQ8_0 | 12.6 t/sQ6_K |
| Qwen3.6 35B · 3B active | 194.3 t/sFP16 | 12.6 t/sFP16 |
| DeepSeek V4 Flash 284B · 13B active | 243.3 t/sQ4_K_M | 33.5 t/sQ2_K |
| Qwen3.6 27B | 54.0 t/sFP16 | 3.5 t/sFP16 |
| Gemma 4 26B · 4B active | 145.8 t/sFP16 | 9.5 t/sFP16 |
Change the context, RAM or model in the calculator: AMD Instinct MI300X 192GB · AMD Strix Halo 128GB
Every report on each card, with its source: AMD Instinct MI300X 192GB · AMD Strix Halo 128GB