InquiringMinds-AI / longcat family / text-generation
longcat-flash-lite
meituan/longcat-flash-lite
Run locally Smallest indexed GGUF / needs Ollama
ollama run hf.co/meituan/longcat-flash-lite/LongCat-Flash-Lite-Q3_K_L.gguf Benchmarks
Where it scores.
General Provisional
65.3
Coding Provisional
58.8
Math Provisional
64.8
Reasoning Provisional
65.0
Normalized 0–100 across indexed models.
Runnable variants
Pick a size.
| Precision | Format | Size | Params | File |
|---|---|---|---|---|
| Q3_K_L / smallest | GGUF | 32.8 GB | — | LongCat-Flash-Lite-Q3_K_L.gguf |
| Q4_K_M | GGUF | 40.2 GB | — | LongCat-Flash-Lite-Q4_K_M.gguf |
| Q5_K_M | GGUF | 48.0 GB | — | LongCat-Flash-Lite-Q5_K_M.gguf |
| Q6_K | GGUF | 56.3 GB | — | LongCat-Flash-Lite-Q6_K.gguf |
| Q8_0 | GGUF | 72.9 GB | — | LongCat-Flash-Lite-Q8_0.gguf |
| BF16 | GGUF | 137.1 GB | — | LongCat-Flash-Lite-bf16.gguf |
Sizes are file sizes, not peak runtime memory.
Raw benchmarks
The inputs.
| Source | Task | Raw | Normalized |
|---|---|---|---|
| ZeroEval | AIME2025 | 63.2 | 63.2 |
| ZeroEval | GPQA | 66.8 | 66.8 |
| ZeroEval | SWEBenchVerified | 54.4 | 54.4 |
From the Hugging Face model card
About this model.
From the Hugging Face model card