Leaderboard / Xiaomi (MiMo)
MiMo-VL-7B-RL
Xiaomi (MiMo) · MiMo · released 2025-05-30 · data checked 2026-11-01 Needs verification
MiMo-VL-7B-RL is a 8.3B-parameter dense model from Xiaomi (MiMo) (China), released 2025-05-30 under the MIT license. It doesn't have enough reported benchmarks for an index score yet. It needs about 6.9 GB of memory at 4-bit with an 8K-token context.
Small LM Index
—
Needs 2 core benchmarks (has 0)
Parameters
8.3B
Dense
Price per 1M tokens
—
No hosted API on OpenRouter; self-host
Context window
32K
tokens
Benchmarks
Each bar shows this model's score. The tick marks the best small model on that benchmark.
No benchmark results for this release yet. Know of one? Send it.
Specifications
- Lab
- Xiaomi (MiMo) (CN · China)
- Architecture
- Dense transformer
- Total parameters
- 8.3B
- Active parameters
- All (dense)
- Size class
- Small
- Context window
- 32K tokens
- Input modalities
- text, image, video
- Reasoning
- Reasoning (thinking)
- License
- MIT
- Openness
- Open weights
- Memory to run
- ~6.9 GB at 4-bit, 8K context (more sizes)
- Hugging Face
- 1.4K downloads (30 days) · 171 likes
Compare with
- MiMo-VL-7B-RL vs DeepSeek-R1-0528-Qwen3-8B (8.2B, index 53.1)
- MiMo-VL-7B-RL vs Qwen3 8B (8.2B, index 48.5)
- MiMo-VL-7B-RL vs Granite 4.2 8B (8B, index 63.5)
Sources
Something wrong here? Report it.
Run it locally
Uses unsloth/MiMo-VL-7B-RL-GGUF (Q4_K_M). Swap the tag for another size: BF16, IQ4_NL, IQ4_XS, Q2_K, Q2_K_L, Q3_K_M, Q3_K_S, Q4_0….
Ollama
ollama run hf.co/unsloth/MiMo-VL-7B-RL-GGUF:Q4_K_Mllama.cpp
llama-server -hf unsloth/MiMo-VL-7B-RL-GGUF:Q4_K_MThen open http://localhost:8080 for a chat window.
vLLM (GPU server)
vllm serve XiaomiMiMo/MiMo-VL-7B-RLFull-precision weights, for a server GPU.
Memory needed: weights, context cache and runtime buffers.
| Quantization | 4K context | 32K context |
|---|---|---|
| 16-bit F16 | 18 GB | 22 GB |
| 8-bit Q8_0 | 10 GB | 14 GB |
| 4-bit Q4_K_M | 6.3 GB | 10 GB |