Qwen 4 series small base; 8B dense model, multilingual + code + instruction following. 1M context window.
0
Quantized builds
4
Benchmark records
Quantized builds
Community and official quantized releases; "linked records" counts only benchmarks tied to that exact release.
No quantized builds cataloged yet.
Benchmark data
4 configurations
| Hardware | Framework | Quant | Decode | VRAM used | Samples | Evidence |
|---|---|---|---|---|---|---|
| NVIDIA RTX 5070 SUPER | Strata | IQ4_XS | 208.4 tok/s | 4.8 GB | 1 | L0 Self-reported |
| NVIDIA RTX 5080 SUPER | llama.cpp | Q4_K_M | 178.3 tok/s | 5.4 GB | 1 | L0 Self-reported |
| NVIDIA RTX 5090 | vLLM | Q5_K_M | 258.2 tok/s | 6.4 GB | 1 | L0 Self-reported |
| NVIDIA RTX 4090 | llama.cpp | Q4_K_M | 160.5 tok/s | 5.4 GB | 1 | L0 Self-reported |
4 of these records are not linked to a specific quantized build; the full set is on the search page.
Community discussion
No discussions yet — start the first one.
Start a discussion