M1 Ultra 128GB vs M3 Ultra 96GB for local LLMs
11 reports on the M1 Ultra 128GB and 7 on the M3 Ultra 96GB
Which is faster for local LLMs?
On gpt-oss 117B · 5.1B active at 4-bit, the M1 Ultra 128GB has 65.5 generation tokens/s (one run); prompt processing 392.4 tokens/s (one run); the M3 Ultra 96GB has 73.0 generation tokens/s (one run); prompt processing 347.0 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 about the same on both (819 GB/s on the M1 Ultra 128GB, 819 on the M3 Ultra 96GB).
- Memory
- 128GB unified
- Memory bandwidth
- 819 GB/s
- FP16 compute
- 21 TFLOPS
- Reports
- 11
- Memory
- 96GB unified
- Memory bandwidth
- 819 GB/s
- FP16 compute
- 21.3 TFLOPS
- Reports
- 7
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 | M1 Ultra 128GB | M3 Ultra 96GB |
|---|---|---|
| gpt-oss 117B · 5.1B active4-bit | 65.5one runPP 392.4 (one run)engine not statedcontext not stated | 73.0one runPP 347.0 (one run)MLXcontext 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 | M1 Ultra 128GB | M3 Ultra 96GB |
|---|---|---|
| gpt-oss 117B · 5.1B active | 42.7 t/sQ5_K_S | 68.5 t/sQ3_K_M |
| Qwen3.8 27B | 7.5 t/sFP16 | 7.9 t/sFP16 |
| Qwen3.8 125B · 6B active | 34.0 t/sQ5_K_S | 55.1 t/sQ3_K_M |
| Qwen3.6 35B · 3B active | 23.5 t/sFP16 | 57.1 t/sQ8_0 |
| DeepSeek V4 Flash 284B · 13B active | 53.5 t/sQ2_K | doesn't fit at these settings |
| Qwen3.6 27B | 7.5 t/sFP16 | 7.9 t/sFP16 |
| Gemma 4 26B · 4B active | 20.2 t/sFP16 | 19.0 t/sFP16 |
Change the context, RAM or model in the calculator: M1 Ultra 128GB · M3 Ultra 96GB
Every report on each card, with its source: M1 Ultra 128GB · M3 Ultra 96GB