Comparison Not counted
Which engine runs LFM2.5 1.2B Instruct best on M5 Max · 64 GiB?
- Device
- M5 Max · 64 GiB (Apple silicon Macs)
- OS
- macOS 27
- Model
- LFM2.5 1.2B Instruct, 1.2B parameters
- Weights
- 4-bit
- Workload
- 2048 input / 128 output: 2,048 tokens in, 128 out
- Decoding
- Greedy, batch 1, context 4,096
- Power
- Plugged in
Ranking
Balanced: Decode speed, time to first token and peak memory, weighted equally.
Every experiment
Medians over valid trials, with the lowest and highest beneath. Eligible experiments are complete and passed their output check. The ranking above selects each engine's configuration for this objective when its required metrics are measured.
| Experiment | Ranking eligibility | Decode tok/s, higher is better | First token ms, lower is better | Memory GiB, lower is better | Prefill tok/s, higher is better | Valid trials |
|---|---|---|---|---|---|---|
| llama.cpp b12110 · Metal · Q4_K_M | Partial Partial: 3 of 6 planned trials were valid. | 421.8 range417.0–436.0 | 137 range137–138 | Not measured | 15,026 range14,937–15,064 | 3of 6 planned |
| MLX LM 0.32.2 · Metal · mlx-affine-4bit-g64 | Partial Partial: 2 of 6 planned trials were valid. | 518.9 range518.2–519.6 | 90.2 range89.6–90.8 | Not measured | 22,874 range22,714–23,033 | 2of 6 planned |
Every trial, metric by metric
The line runs from an experiment's lowest to its highest valid trial, the dot is the median and each tick is one trial. Every scale starts at zero.
Caveats
- Publisher cards identify the base model but do not pin the exact export source checkpoint revision; exact source-weight identity is unverified.
- GGUF and MLX may differ in quantization, effective KV cache precision, kernels, and activations.
About this comparison
Worked out from its experiments: every experiment here shares the device, the OS major version, the power state, the base model, the quantization class and the workload. Measured under methodology v0.3. Comparison id glenn-m5-max-64gb--macos-27--lfm2.5-1.2b-instruct--4-bit--liquid-2048-128.