←News detail

UnslothUpdated Nov 2 23:14

Unsloth releases DeepSeek-V4.1-Flash-1017 GGUF benchmark results

AI summary

Unsloth ran benchmarks such as Terminal Bench and DeepSWE on the GGUF quantized versions of DeepSeek-V4.1-Flash-1017 at a 512K context, and said it ranks highest overall. Among them, the 1-bit Unsloth GGUF scored 68.1 on DeepSWE, 72.2 on Terminal-Bench, and 52.7 on AutomationBench, leading other quantized versions by more than 10%.

Quoted post

Unsloth AI

@UnslothAI

We’re releasing new DeepSeek-V4.1-Flash-1017 GGUFs, ranking highest across benchmarks. Dynamic V3.1 leads across nearly all benchmarks: GPQA Diamond, AIME25, LiveCodeBench v6, MMLU-Pro, Aider & more. Run on 64GB+ RAM. GGUF: https://t.co/1kD14VTAYP Blog: https://t.co/YPEmDLas7d https://t.co/BdPoyeSQBe

View original

We’re releasing new DeepSeek-V4.1-Flash-1017 GGUFs, ranking highest across benchmarks. Dynamic V3.1 leads across nearly all benchmarks: GPQA Diamond, AIME25, LiveCodeBench v6, MMLU-Pro, Aider & more. Run on 64GB+ RAM. GGUF: https://t.co/1kD14VTAYP Blog: https://t.co/YPEmDLas7d https://t.co/BdPoyeSQBe

View original post

Body

We benchmarked DeepSeek-V4.1-Flash-1017 GGUFs on Terminal Bench, DeepSWE & more on 512K context. Unsloth ranks highest overall.

1-bit Unsloth GGUF scores 68.1 on DeepSWE, 72.2 on Terminal-Bench, 52.7 on AutomationBench. >10% ahead of other quants.

GGUF: https://t.co/1kD14VTAYP https://t.co/dEK5xmmibe

Source

Unsloth