Unified MemoryBenchmarks / Which Small AI Model Should You Run on a Mac? We Ran 312 Tests / Models
K2-Horizon 0.9B
IFM/K2-Horizon-0.9B-GGUF:Q4_K_M · llama.cpp · llama-server version: 0.7.0 (build 11669, commit 620d2225c)
#8 of 8
overall, text jobs
55.9
quality score
218.4
median tokens/s
1.33 GB
RAM with 8K context filled
0.62 GB
download size
Score per job
| Job | Accuracy | Pass | Easy | Medium | Hard | Median latency | Tok/s | Job time | Errors |
|---|---|---|---|---|---|---|---|---|---|
| Assistant actions | 58.4 | 46.0% | 60.0% | 52.9% | 27.8% | 0.26 s | 204.3 | 19.6 s | 0 |
| Ask my documents | 41.6 | 27.5% | 50.0% | 15.4% | 20.0% | 0.64 s | 200.7 | 31.7 s | 0 |
| Rewrite and proofread | 49.1 | 4.8% | 0.0% | 14.3% | 0.0% | 0.43 s | 218.4 | 19.6 s | 0 |
| Summarize + extract | 74.9 | 20.5% | 26.7% | 23.1% | 12.5% | 0.77 s | 210.2 | 46.5 s | 0 |
| Translate | 51.9 | 7.5% | 15.4% | 7.7% | 0.0% | 0.36 s | 220.2 | 14.2 s | 0 |
| Sort and triage | 59.8 | 51.8% | 52.9% | 63.2% | 40.0% | 0.16 s | 269.0 | 8.40 s | 0 |
Easy / medium / hard columns are pass rates within each difficulty tier.
Memory and loading
| Download size | 0.62 GB |
| Loaded, idle | 1.22 GB |
| In use (8K context) | 1.24 GB |
| 8K context filled | 1.33 GB |
| Server peak during the jobs (incl. reserved context) | 7.95 GB |
| Load time | 20.2 s |
Measured on Apple M4 Max, 36 GB, macOS 27.0.1. How memory was measured.