Leaderboard / Microsoft (Phi)
Phi-4-reasoning-vision-15B
Microsoft (Phi) · Phi-4 · released 2026-03 · data checked 2026-11-01 Needs verification
Phi-4-reasoning-vision-15B is a 15B-parameter dense model from Microsoft (Phi) (United States), released 2026-03 under the MIT license. It doesn't have enough reported benchmarks for an index score yet. It needs about 11.4 GB of memory at 4-bit with an 8K-token context.
Benchmarks
Each bar shows this model's score. The tick marks the best medium model on that benchmark.
No benchmark results for this release yet. Know of one? Send it.
Specifications
- Lab
- Microsoft (Phi) (US · United States)
- Architecture
- Dense transformer
- Total parameters
- 15B
- Active parameters
- All (dense)
- Size class
- Medium
- Context window
- 32K tokens
- Input modalities
- text, image
- Reasoning
- Reasoning (thinking)
- License
- MIT
- Openness
- Open weights
- Memory to run
- ~11.4 GB at 4-bit, 8K context (more sizes)
Compare with
- Phi-4-reasoning-vision-15B vs Apriel 1.6 15B Thinker (14.9B, index 60.9)
- Phi-4-reasoning-vision-15B vs Phi-4-reasoning-plus (14.7B, index 54.4)
- Phi-4-reasoning-vision-15B vs Phi-4 (14.7B, index 44.7)
Sources
Something wrong here? Report it.
Run it locally
No quantized build from a well-known publisher yet; check the model card for instructions.
Memory needed: weights, context cache and runtime buffers (context cache estimated: attention layout not published).
| Quantization | 4K context | 32K context |
|---|---|---|
| 16-bit F16 | 32 GB | 37 GB |
| 8-bit Q8_0 | 17 GB | 22 GB |
| 4-bit Q4_K_M | 11 GB | 16 GB |