Data and index / Other
K2 Horizon 0.9B Q4_K_M
on Mac, M4 Pro, 48 GB
Fits with about 43 GB to spare. Finished 10 of 15 runs inside a 600 token limit.
- Download this entryAs a CSV file
- How we testHow a figure gets in
- Run it yourselfThe script, step by step
- Cite this entry
- Follow Onticpost
Articles on K2 Horizon 0.9B Q4_K_M
Run history
Every run
| Date | Speed | Memory |
|---|---|---|
| 30 October 2026 | 224.7 t/s | 4.7 GB |
Change over time
How each figure moved, from the earliest run in each period to the latest.
The table fills once a second run is recorded.
Did this match your machine?
Readers who ran the script tell us whether they saw the same.
Against the maker's claim
The maker publishes no speed or memory figure for this build, so there is nothing to set our figures against.
How we measured
The set up for this entry has not been written down yet.
Run it yourself
Send us your result in the same format and it joins the index as a community entry, with your sample size.
The script needs Ollama or LM Studio running on your machine, with the model loaded. It changes nothing and sends nothing; it prints the line to send us.
About K2 Horizon 0.9B Q4_K_M
What is K2 Horizon 0.9B?
K2 Horizon 0.9B is a compact dense reasoning model from IFM with a 128,000 token context window, released under the Apache 2.0 licence. This entry measures the Q4_K_M build, a 0.67 GB file, in LM Studio on a Mac with an M4 Pro chip and 48 GB of memory.
What was measured
Fifteen runs across five tasks in LM Studio, llama.cpp Metal runtime 2.47.0, context 65,536 tokens, 600 tokens allowed per run, on macOS 27.0.1. Writing speed is the middle run. Memory is the larger of the readings taken before and after the runs. 10 of the 15 runs finished inside the allowance. In 4 the whole allowance went on thinking and no answer was written. In 1 the limit cut the answer off part way.
Other figures
| Measure | Result |
|---|---|
| Slowest and fastest run | 210.67 and 229.10 tokens a second |
| Wait for the first token, short prompt | 0.03 seconds |
| Wait for the first token, 3,660 token prompt | 1.9 seconds |
| Runs that finished inside 600 tokens | 10 of 15 |
| Runs with no answer inside 600 tokens | 4 of 15 |
| Model file on disk | 0.67 GB |
Measured with the same script as every other entry on this machine.
Sources
Cite this page
Hill. "K2 Horizon 0.9B Q4_K_M". Onticpost, published 2 November 2026, updated 31 October 2026. https://onticpost.com/index/k2-horizon-0-9b-m4-pro-48gb/
Updated 31 October 2026. This address stays the same when the piece is updated.
Similar entries: the same model
No other machine has run this model in the index yet. Run the script above and yours can be the first.
Similar entries: this machine
| Entry | Speed | Fit |
|---|---|---|
| Spark X2.6 4B Q4_K_M | 64.1 |  |
| Nemotron 3.5 Bolt E4B Q4_K_M | 52.1 | |
| Nanbeige4.3 33B Q4_K_M | 9.7 |   |
| MiMo V2.6 Distill Qwen 9B Q8_0 | 24.3 |  |
| Flint Q4_K_M | 71.5 |  |
| GLM 4.7 Flash Q4_K_M | 56.2 | |
Subscribe to our newsletter
Checked: what AI can do for your business, checked by humans. Free, every Friday. One email a week, leave any time.
Free, every Friday. We send a link to confirm first. Our privacy policy says what we keep.