M3 Ultra 256GB vs NVIDIA RTX 4060 Laptop 8GB for local LLMs
12 reports on the M3 Ultra 256GB and 3 on the NVIDIA RTX 4060 Laptop 8GB
Which is faster for local LLMs?
On Qwen3.5 9B at 4-bit, the M3 Ultra 256GB has 107.5 generation tokens/s (one run); the NVIDIA RTX 4060 Laptop 8GB has 37.7 generation tokens/s (one run); prompt processing 1828.8 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 3.2x higher on the M3 Ultra 256GB (819 GB/s on the M3 Ultra 256GB, 256 on the NVIDIA RTX 4060 Laptop 8GB).
- Memory
- 256GB unified
- Memory bandwidth
- 819 GB/s
- FP16 compute
- 28.4 TFLOPS
- Reports
- 12
- Memory
- 8GB
- Memory bandwidth
- 256 GB/s
- FP16 compute
- 59 TFLOPS
- Reports
- 3
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 256GB | NVIDIA RTX 4060 Laptop 8GB |
|---|---|---|
| Qwen3.5 9B4-bit | 107.5one runengine not statedcontext not stated | 37.7one runPP 1828.8 (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 256GB | NVIDIA RTX 4060 Laptop 8GB |
|---|---|---|
| Qwen3.5 9B | 23.9 t/sFP16 | 41.7 t/sQ3_K_S |
| Qwen3.8 27B | 8.0 t/sFP16 | 1.6 t/sQ6_K, layers on CPU |
| Qwen3.8 125B · 6B active | 27.3 t/sQ8_0 | doesn't fit at these settings |
| DeepSeek V4 Flash 284B · 13B active | 36.0 t/sQ4_K_M | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 28.7 t/sFP16 | 14.3 t/sQ5_K_M, experts in RAM |
| Qwen3.6 27B | 8.0 t/sFP16 | 1.6 t/sQ6_K, layers on CPU |
| Gemma 4 26B · 4B active | 21.5 t/sFP16 | 9.1 t/sQ6_K, experts in RAM |
Change the context, RAM or model in the calculator: M3 Ultra 256GB · NVIDIA RTX 4060 Laptop 8GB
Every report on each card, with its source: M3 Ultra 256GB · NVIDIA RTX 4060 Laptop 8GB