Open-weight vision-language model from MiniMax, released 2026-06-02, 427.0B total, a bespoke open-weights licence. MiniMax's MoE flagship at ~427B total parameters, with image-text understanding.
0
Quantized builds
12
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
12 configurations
| Hardware | Framework | Quant | Decode | VRAM used | Samples | Evidence |
|---|---|---|---|---|---|---|
| NVIDIA RTX 5070 Ti | SGLang | IQ4_XS | 3.2 tok/s | 16 GB | 1 | L0 Self-reported |
| NVIDIA RTX 5070 Ti | SGLang | IQ3_S | 4.2 tok/s | 16 GB | 1 | L0 Self-reported |
| NVIDIA RTX 5070 Ti | vLLM | IQ4_XS | 3.3 tok/s | 16 GB | 1 | L0 Self-reported |
| NVIDIA RTX 5070 Ti | vLLM | IQ3_S | 4.4 tok/s | 16 GB | 1 | L0 Self-reported |
| NVIDIA RTX 5090 | SGLang | IQ4_XS | 6.4 tok/s | 32 GB | 1 | L0 Self-reported |
| NVIDIA RTX 5090 | SGLang | IQ3_S | 8.5 tok/s | 32 GB | 1 | L0 Self-reported |
| NVIDIA RTX 5090 | vLLM | IQ4_XS | 6.6 tok/s | 32 GB | 1 | L0 Self-reported |
| NVIDIA RTX 5090 | vLLM | IQ3_S | 8.8 tok/s | 32 GB | 1 | L0 Self-reported |
| NVIDIA RTX 4090 | SGLang | IQ4_XS | 3.6 tok/s | 24 GB | 1 | L0 Self-reported |
| NVIDIA RTX 4090 | SGLang | IQ3_S | 4.8 tok/s | 24 GB | 1 | L0 Self-reported |
| NVIDIA RTX 4090 | vLLM | IQ4_XS | 3.7 tok/s | 24 GB | 1 | L0 Self-reported |
| NVIDIA RTX 4090 | vLLM | IQ3_S | 5 tok/s | 24 GB | 1 | L0 Self-reported |
12 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