Phi-3.5-mini-instruct
microsoftmittext

Phi-3.5-mini-instruct

Updated Nov 21, 2026
Parameters
3.8B
Context
131,072
License
mit
Q4 GGUF
2.39 GB
Updated
Nov 21, 2026

Q4 GGUF download: MaziyarPanahi/Phi-3.5-mini-instruct-GGUF - 2.39 GB on disk, read 2026-11-19. VRAM figures above are estimates; this is the actual file size.

Standard benchmarks

Performance across standard evaluations

BenchmarkScore
GSM8K86.2

Additional scores from Hugging Face OpenEvals official leaderboards - updated 2026-11-21.

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Runs on your 24 GB - best at FP16
4 of 4 quantizations fit Phi-3.5-mini-instruct with real runtime overhead.
Q4_K_M
2 GB
Q5_K_M
3 GB
Q8_0
4 GB
FP16
8 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve microsoft/Phi-3.5-mini-instruct

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

Phi-3.5-mini-instruct is a 3.8B-parameter mit model from microsoft. At Q4_K_M it needs roughly 2 GB of VRAM, placing it in the CPU / ≤4 GB hardware tier.

PopularityLink to this section

Phi-3.5-mini-instruct has 340,333 downloads in the last month on HuggingFace and 1,297 likes.

From the community

What users are saying

“What do you mean by "safe"? IMO, if a model is too safe then it become boring. That's why they say "don't play it safe in life". I like LLMs for entertainment value so if a model is too safe then it is less entertaining.”

“Hi guys, I met the same problem, too. I just fixed this error by degrading the transformer version to transformers=4.45.0, and then it works.”

“I've been successfully using the quantized versions (some users have uploaded various quantized versions to HF). The GGUFs run pretty efficiently. Have you tried any of them?”

Frequently asked

Quick answers to common questions

How much VRAM does Phi-3.5-mini-instruct need?

Phi-3.5-mini-instruct with 3.8B parameters needs approximately 2 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is Phi-3.5-mini-instruct better than other microsoft models?

Phi-3.5-mini-instruct has 3.8B parameters with 131,072 context - a strong choice for coding, long-context, edge.

What license is Phi-3.5-mini-instruct under?

Phi-3.5-mini-instruct is released under the mit license, making it suitable for most commercial and personal projects.

What hardware runs Phi-3.5-mini-instruct well?

With 3.8B parameters, Phi-3.5-mini-instruct requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.

What is the best quantization for Phi-3.5-mini-instruct?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~3 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

How long can Phi-3.5-mini-instruct's context window handle?

Phi-3.5-mini-instruct supports a 131,072-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.

What models compete with Phi-3.5-mini-instruct?

Phi-3.5-mini-instruct competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec