Compare
Compare models side by side
Choose up to 4 models to see their file size, memory, license and third-party evaluations side by side.
Comparison table
| Item | Qwen3.8-Flash-Next-FP4-Local-Strata hardhant ✕ Remove |
|---|---|
| Parameters | 51.2B |
| Architecture | strata-ple |
| Max context length | - |
| Representative quantization and size Measured | BF16 · 1.27 GB |
| Memory at 8K Estimated | 2.66 GB |
| Memory at 32K Estimated | 3.34 GB |
| VRAM it fits (8K) Estimated | VRAM 4 GB+ |
| Smallest quantization (8K) Estimated | BF16 · 1.27 GB → 2.66 GB |
| License | NVIDIA Open Model Agreement Commercial OK |
| llama.cpp support | Not supported by mainline llama.cpp (as of b12025) |
| Downloads (30 days, total) | 32,070 |
| Human preference (LMArena) | - |
| Capabilities (Epoch AI) | - |
| Hard science (GPQA) | - |
- The representative quantization is Q4_K_M (or the smallest one if missing) from the source with the most downloads. Memory is estimated with an f16 KV cache.
- Third-party evaluations are other organizations' values for the original model before quantization, not this site's rating (sources are on the ranking page).
- This site does not judge which model is better or give an overall score.