Phi-3 Medium 14B
Phi-3's mid-tier model with extended 128K context. MIT licence. Strong reasoning relative to its parameter count thanks to Microsoft's heavy investment in synthetic training data.
- Parameters
- 14B
- Context length
- 128K
- Modality
- text
- Released
- 2024-05-21
- Tokenizer
- LlamaTokenizer
Memory & hardware
- VRAM (fp16)
- 28 GB
- VRAM (Q4)
- 8.4 GB
- Recommended
- RTX 4090 24GB
- Quantizations
- fp16, q8_0, q5_k_m, q4_k_m
Benchmarks
Hosted inference pricing
No provider we track publishes a per-token price for this model today. What each one used to offer is listed below.
No longer listed
Providers that used to serve this model. We don't republish their old rates — the dates below are the provider's own.
- togetherNot in Together AI’s serverless catalogue when we checked on 20 September 2026.Source ↗
Run it yourself
Drop-in commands for the three most common open-source inference paths. The Ollama tag is a best-effort match against the registry; verify the size variant before pulling.
ollama run phi3
vllm serve microsoft/Phi-3-medium-128k-instruct
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-medium-128k-instruct")
model = AutoModelForCausalLM.from_pretrained(
"microsoft/Phi-3-medium-128k-instruct", device_map="auto", torch_dtype="auto"
)microsoft/Phi-3-medium-128k-instruct Related models
Same family or similar size — useful when shopping around.
14B model trained primarily on synthetic data. Punches above its weight on reasoning, especially MATH and GPQA. MIT licensed. A standout choice when you want strong reasoning quality without paying 70B-tier hardware costs. Phi-4 in particular demonstrated that careful synthetic-data curation can extract frontier-class reasoning from a relatively small dense model.
- Context
- 16K
- License
- mit
- VRAM Q4
- 8.4 GB
Mid-size Qwen2.5 with broad task coverage. The sweet spot for users who want noticeably better quality than 7B but can't justify the hardware footprint of 32B or 72B.
- Context
- 128K
- License
- apache-2-0
- VRAM Q4
- 8.4 GB
Larger OLMo 2 release. Same fully-open philosophy as the 7B variant. The 13B size makes it more competitive with mainstream production-grade chat models.
- Context
- 4K
- License
- apache-2-0
- VRAM Q4
- 7.8 GB
Mid-size Llama 2 chat model. Deprecated in most 2025 workloads by Llama 3.1 8B, but remains the baseline against which many post-2023 fine-tunes report.
- Context
- 4K
- License
- llama-2
- VRAM Q4
- 7.8 GB
Meta's April 2025 mixture-of-experts release. 17B active parameters across 16 experts (109B total). Natively multimodal with an unprecedented 10M-token context window — a leap far beyond Llama 3's 128K. Scout was designed to run on a single GPU at Q4 while beating Llama 3.3 70B on reasoning and multilingual benchmarks. The Llama 4 licence tightened acceptable-use provisions vs Llama 3.
- Context
- 10.0M
- License
- llama-4
- VRAM Q4
- 10.2 GB
Larger Llama 4 sibling of Scout — 17B active across 128 experts (400B total). 1M-token native context. Positioned as GPT-4o-class on chat and reasoning while remaining tractable on a single high-end host at fp8. Multimodal from the ground up; instruction-tuned by Meta with a heavier synthetic-data pipeline than Llama 3.
- Context
- 1.0M
- License
- llama-4
- VRAM Q4
- 10.2 GB