M1 16GB vs M1 Ultra 128GB for local LLMs
3 reports on the M1 16GB and 4 on the M1 Ultra 128GB
Which is faster for local LLMs?
On Gemma 4 8B at 4-bit, the M1 16GB has 8.2 generation tokens/s (one run); the M1 Ultra 128GB has 69.7 generation tokens/s (one run); prompt processing 1172.9 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 12.0x higher on the M1 Ultra 128GB (68 GB/s on the M1 16GB, 819 on the M1 Ultra 128GB).
- Memory
- 16GB unified
- Memory bandwidth
- 68 GB/s
- FP16 compute
- 2.6 TFLOPS
- Reports
- 3
- Memory
- 128GB unified
- Memory bandwidth
- 819 GB/s
- FP16 compute
- 21 TFLOPS
- Reports
- 4
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 16GB | M1 Ultra 128GB |
|---|---|---|
| Gemma 4 8B4-bit | 8.2one runUnsloth Studio131K context | 69.7one runPP 1172.9 (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 | M1 16GB | M1 Ultra 128GB |
|---|---|---|
| Gemma 4 8B | 9.7 t/sQ5_K_M | 25.2 t/sFP16 |
| Qwen3.8 27B | doesn't fit at these settings | 7.5 t/sFP16 |
| Qwen3.8 125B · 6B active | doesn't fit at these settings | 34.0 t/sQ5_K_S |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | 53.5 t/sQ2_K |
| Qwen3.6 35B · 3B active | doesn't fit at these settings | 23.5 t/sFP16 |
| Qwen3.6 27B | doesn't fit at these settings | 7.5 t/sFP16 |
| Gemma 4 26B · 4B active | doesn't fit at these settings | 20.2 t/sFP16 |
Change the context, RAM or model in the calculator: M1 16GB · M1 Ultra 128GB
Every report on each card, with its source: M1 16GB · M1 Ultra 128GB