Underdog Saluki 27B
ConwayResearch/Underdog-Saluki-27B-1.0
LocalIQ2_XS10.2 GB at 32K23 tok/s on M5 Pro256K context
33
50 of 153 test cases fully passed
Scores by task
Scores give partial credit. Passed counts fully correct answers only. Select a task to read its test cases.
What it built
What it wrote for showcase prompts, running live in your browser.
Run it yourself
The exact build behind this score, and the command that serves it.
- Local
- llama.cpp
- IQ2_XS
- -ngl -1 --temp 0.6 --top-p 0.95 --top-k 20 --reasoning on
- 256K
- 10.2 GB at 32K
- Apple M5 Pro, 48 GB
- 23 tok/s
- Not measured
- Not measured
- 5m 15s
- 2026-10-15
llama.cpp
llama-server -hf ConwayResearch/Underdog-Saluki-27B-1.0:IQ2_XS --port 9931 -c 262144 -ngl -1 --temp 0.6 --top-p 0.95 --top-k 20 --reasoning onPulls the GGUF from Hugging Face and serves an OpenAI-compatible endpoint on port 9931.
Memory it needs
7.3 GB of weights, 746 MB of runtime, and 69 MB per 1K tokens of context.
| Context | Memory | Smallest Mac | Smallest GPU |
|---|---|---|---|
| 8K | 8.6 GB | 16 GB | 12 GB |
| 32K | 10.2 GB | 16 GB | 12 GB |
| 128K | 16.8 GB | 32 GB | 24 GB |
| 256K | 25.4 GB | 36 GB | 32 GB |
One email when a new model lands on the board or in the showcase. Unsubscribe anytime.