Model datasheet · Phi
Phi-4-reasoning-vision
Microsoft's selective-reasoning vision model — it decides when to think. Catalogued for completeness with a hard local caveat: llama.cpp cannot run its vision tower, so local GGUFs are text-only; the headline capability needs the full weights via transformers.
- Vendor
- Microsoft
- Architecture
- Dense · 15B
- Context
- 16,384 tokens
- License
- MIT
- Released
- 2026-03-04
- Vision
- Yes
→ GGUF (llama.cpp / LM Studio / Ollama) → MLX (Apple Silicon)
§1 Characteristics by quantization band
— Not yet rated · contributions welcome —
Q4–Q5 — 4–5 bit
9GB weights · e.g. Q4_K_M , mlx-4bit + KV: 1.6GB at 8K · 3.1GB at 32K · 3.1GB at 128K— Not yet rated · contributions welcome —
— Not yet rated · contributions welcome —
FP16 — full precision (fp16/bf16)
29GB weights · e.g. fp16 + KV: 1.6GB at 8K · 3.1GB at 32K · 3.1GB at 128K— Not yet rated · contributions welcome —
§2 Known issues & what fixes them
Its reason-to-exist doesn't work in llama.cpp: there is no support for the phi4-siglip vision tower, so every GGUF is a text-only backbone (which is why our text dimensions sit unrated). An mlx-community 4-bit build exists and may be the practical local vision path on Apple Silicon via mlx-vlm — unverified by us.
On a Mac, try the mlx-community 4-bit build with mlx-vlm. Elsewhere, watch llama.cpp for phi4-siglip support; until then vision needs full weights via transformers.
For local vision today, use Gemma 3, Mistral Small 4, or Qwen3.8 instead.
Evidence · 2 sources · community-consensus
- Community GGUF (text-backbone-only conversion, vision tower unsupported) (other, 2026-08-30)
- Phi-4-reasoning-vision model card (vision-only benchmark table) (vendor, 2026-08-30)
Inherits Phi-4's 16K window — cramped for 2026, especially for the multi-image reasoning it was built for.
Chunked retrieval keeps requests inside 16K.
Evidence · 1 source · anecdotal
- Model card (16,384 context) (vendor, 2026-08-30)