NVIDIA RTX 3080 20GB vs AMD Strix Halo 128GB for local LLMs
14 reports on the NVIDIA RTX 3080 20GB and 313 on the AMD Strix Halo 128GB
Which is faster for local LLMs?
On Qwen3.8 27B at 4-bit, the NVIDIA RTX 3080 20GB has 25.7 generation tokens/s (2 runs); prompt processing 997.0 tokens/s (one run); the AMD Strix Halo 128GB has 13.1 generation tokens/s (4 runs); prompt processing 378.2 tokens/s (3 runs). 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 3.0x higher on the NVIDIA RTX 3080 20GB (760 GB/s on the NVIDIA RTX 3080 20GB, 256 on the AMD Strix Halo 128GB).
- Memory
- 20GB
- Memory bandwidth
- 760 GB/s
- FP16 compute
- 119 TFLOPS
- Reports
- 14
- Memory
- 128GB unified
- Memory bandwidth
- 256 GB/s
- FP16 compute
- 59 TFLOPS
- Reports
- 313
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 | NVIDIA RTX 3080 20GB | AMD Strix Halo 128GB |
|---|---|---|
| Qwen3.8 27B4-bit | 25.72 runsPP 997.0 (one run)llama.cpp, 1 not stated96K context, 1 not stated | 13.14 runsPP 378.2 (3 runs)llama.cpp, 1 not stated32K context, 3 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 | NVIDIA RTX 3080 20GB | AMD Strix Halo 128GB |
|---|---|---|
| Qwen3.8 27B | 35.4 t/sQ3_K_M | 3.5 t/sFP16 |
| Qwen3.8 125B · 6B active | 19.1 t/sQ2_K, experts in RAM | 12.6 t/sQ6_K |
| Qwen3.6 35B · 3B active | 140.5 t/sQ3_K_S | 12.6 t/sFP16 |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | 33.5 t/sQ2_K |
| Qwen3.6 27B | 35.4 t/sQ3_K_M | 3.5 t/sFP16 |
| Gemma 4 26B · 4B active | 79.7 t/sQ4_K_S | 9.5 t/sFP16 |
| GLM-5.3 320B · 18B active | doesn't fit at these settings | 11.1 t/sQ2_K |
Change the context, RAM or model in the calculator: NVIDIA RTX 3080 20GB · AMD Strix Halo 128GB
Every report on each card, with its source: NVIDIA RTX 3080 20GB · AMD Strix Halo 128GB