HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Kimi-K2-Instruct-0905-GGUF

unsloth/Kimi-K2-Instruct-0905-GGUF

kind
gguf
quant
gguf (16-bit)
family
kimi
modality
—
root model
moonshotai/Kimi-K2-Instruct-0905
provider
unsloth
license
other
language
—
context
2
library
transformers
vRAM (GB)
—
size on disk
—
downloads
535
likes
53
created
—
last modified
2025-09-06T07:20:31+00:00 (2025)
huggingface
https://huggingface.co/unsloth/Kimi-K2-Instruct-0905-GGUF
tags
transformersggufunslothbase_model:moonshotai/Kimi-K2-Instruct-0905base_model:quantized:moonshotai/Kimi-K2-Instruct-0905license:otherendpoints_compatibleregion:usconversational

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
SWE-bench Verifiedswe65.8SWE-Bench verifiedmedium| SWE-Bench verified | ACC | 69.2 ± 0.63 | 65.8 | 69.6* | 64.2* | 66.0* | 72.7* | 72.5* |
Terminal-Benchagentic-coding37.5Terminal-Benchmedium| Terminal-Bench | ACC | 44.5 ± 2.03 | 37.5 | 37.5* | 39.9* | 31.3* | 36.4* | 43.2* |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.