M3 Ultra 512GB vs AMD Radeon 780M for local LLMs
41 reports on the M3 Ultra 512GB and 6 on the AMD Radeon 780M
Which is faster for local LLMs?
On Qwen3.6 35B · 3B active at 8-bit, the M3 Ultra 512GB has 81.2 generation tokens/s (one run); prompt processing 2324.6 tokens/s (one run); the AMD Radeon 780M has 19.7 generation tokens/s (2 runs); prompt processing 299.4 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 6.8x higher on the M3 Ultra 512GB (819 GB/s on the M3 Ultra 512GB, 120 on the AMD Radeon 780M). Across 2 shared models with generation measurements on both cards, the M3 Ultra 512GB's median is higher on 2 and the AMD Radeon 780M's on 0.
- Memory
- 512GB unified
- Memory bandwidth
- 819 GB/s
- FP16 compute
- 28.4 TFLOPS
- Reports
- 41
- Memory
- shared memory unified
- Memory bandwidth
- not on record
- FP16 compute
- not on record
- Reports
- 6
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 | M3 Ultra 512GB | AMD Radeon 780M |
|---|---|---|
| Qwen3.6 35B · 3B active8-bit | 81.2one runPP 2324.6 (one run)engine not statedcontext not stated | 19.72 runsPP 299.4 (2 runs)llama.cppcontext not stated |
| Gemma 4 26B · 4B active4-bit | 87.8one runPP 2595.3 (one run)llama.cppcontext not stated | 25.0one runPP 208.7 (one run)llama.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 | M3 Ultra 512GB | AMD Radeon 780M |
|---|---|---|
| Qwen3.6 35B · 3B active | 28.7 t/sFP16 | not in the calculator yet |
| Gemma 4 26B · 4B active | 21.5 t/sFP16 | not in the calculator yet |
| Qwen3.8 27B | 8.0 t/sFP16 | not in the calculator yet |
| Qwen3.8 125B · 6B active | 13.6 t/sFP16 | not in the calculator yet |
| DeepSeek V4 Flash 284B · 13B active | 22.6 t/sQ8_0 | not in the calculator yet |
| Qwen3.6 27B | 8.0 t/sFP16 | not in the calculator yet |
| DeepSeek V4.1 Flash 552B · 16B active | 30.0 t/sQ4_K_M | not in the calculator yet |
| GLM-5.3 320B · 18B active | 7.4 t/sQ8_0 | not in the calculator yet |
Change the context, RAM or model in the calculator: M3 Ultra 512GB · AMD Radeon 780M
Every report on each card, with its source: M3 Ultra 512GB · AMD Radeon 780M