AMD Strix Halo 128GB vs NVIDIA V100 32GB for local LLMs
313 reports on the AMD Strix Halo 128GB and 27 on the NVIDIA V100 32GB
Which is faster for local LLMs?
On Qwen3.8 27B at 4-bit, the AMD Strix Halo 128GB has 13.1 generation tokens/s (4 runs); prompt processing 378.2 tokens/s (3 runs); the NVIDIA V100 32GB has 31.4 generation tokens/s (2 runs); prompt processing 940.5 tokens/s (2 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 3.5x higher on the NVIDIA V100 32GB (256 GB/s on the AMD Strix Halo 128GB, 900 on the NVIDIA V100 32GB). Across 2 shared models with generation measurements on both cards, the AMD Strix Halo 128GB's median is higher on 0 and the NVIDIA V100 32GB's on 2.
- Memory
- 128GB unified
- Memory bandwidth
- 256 GB/s
- FP16 compute
- 59 TFLOPS
- Reports
- 313
- Memory
- 32GB
- Memory bandwidth
- 900 GB/s
- FP16 compute
- 125 TFLOPS
- Reports
- 27
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 Strix Halo 128GB | NVIDIA V100 32GB |
|---|---|---|
| Qwen3.8 27B4-bit | 13.14 runsPP 378.2 (3 runs)llama.cpp, 1 not stated32K context, 3 not stated | 31.42 runsPP 940.5 (2 runs)llama.cpp, 1 not stated32K to 128K context |
| Qwen3.6 27B4-bit | 12.0one runPP 322.0 (one run)engine not statedcontext not stated | 32.2one runllama.cppcontext 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 Strix Halo 128GB | NVIDIA V100 32GB |
|---|---|---|
| Qwen3.8 27B | 3.5 t/sFP16 | 22.6 t/sQ6_K |
| Qwen3.6 27B | 3.5 t/sFP16 | 22.6 t/sQ6_K |
| Qwen3.8 125B · 6B active | 12.6 t/sQ6_K | 19.4 t/sQ2_K, experts in RAM |
| Qwen3.6 35B · 3B active | 12.6 t/sFP16 | 81.9 t/sQ5_K_M |
| DeepSeek V4 Flash 284B · 13B active | 33.5 t/sQ2_K | doesn't fit at these settings |
| Gemma 4 26B · 4B active | 9.5 t/sFP16 | 57.5 t/sQ6_K |
| DeepSeek V4.1 Flash 552B · 16B active | doesn't fit at these settings | doesn't fit at these settings |
| GLM-5.3 320B · 18B active | 11.1 t/sQ2_K | doesn't fit at these settings |
Change the context, RAM or model in the calculator: AMD Strix Halo 128GB · NVIDIA V100 32GB
Every report on each card, with its source: AMD Strix Halo 128GB · NVIDIA V100 32GB