' Phi-3.5 Mini Instruct - AEUPH Model Hub
DEPLOY TO RUNPOD SERVERLESS

MODEL DEPLOYMENT Phi-3.5 Mini Instruct Zero Ops. Infinite Scale.

Deploy Phi-3.5 Mini Instruct to RunPod serverless GPUs. Auto-scaling from 0 to 1000+ workers. Pay per second.

Get $10 Free Credits → Deploy Model →
4GBVRAM
2sCold Start
$0.00019/sec (RTX 4090)
∞Auto-Scale
Your Deployment Signal
0%

Deploy Phi-3.5 Mini Instruct

Choose your GPU and deploy instantly. Pay per second. No minimums.

🤖

Phi-3.5 Mini Instruct

microsoft/Phi-3.5-mini-instruct

LLM
≥4GB VRAM ⭐ RTX 3090 Recommended
Deploy to RunPod → Get $10 Free

Model Information

Technical specifications and capabilities for Phi-3.5 Mini Instruct.

📝

Capabilities

  • 128K context window
  • Multilingual (8+ languages)
  • Tool calling / function calling
  • Instruction following
  • Code generation & reasoning
  • RAG-ready embeddings
⚡

Performance

  • ~200 tok/s on RTX 3090
  • ~400 tok/s on RTX 4090
  • ~800 tok/s on A100 40GB
  • FP16 / FP8 quantization
  • Flash Attention 2 support
  • vLLM / TGI optimized
🛠️

Quantization

  • AWQ 4-bit (recommended)
  • GPTQ 4-bit / 8-bit
  • GGUF Q4_K_M / Q8_0
  • FP8 (H100/A100)
  • FP16 (full precision)
  • Custom calibration
🔧

Use Cases

  • Chat assistants & agents
  • Code generation & review
  • RAG & document QA
  • Content generation
  • Reasoning & analysis
  • Fine-tuning ready
🎁 Exclusive Referral Benefits

Deploy on RunPod. Get $10 Free Credits + Lifetime 20% Commissions

Sign up through our partner link and unlock immediate GPU credits, recurring referral revenue, and access to the world's largest serverless GPU fleet. Every model you deploy earns you back.

Sign Up & Claim $10 Free Credits View Referral Dashboard
$10
Instant GPU Credits
20%
Lifetime Commission
$500+
Avg Monthly Earnings
∞
No Cap on Referrals
💰

Instant $10 Free Credits

Sign up via our referral link and get $10 in GPU credits instantly. That's ~55 hours on RTX 3080, ~45 hours on RTX 3090, or ~22 hours on RTX 4090 — completely free. No credit card required for the trial.

🔄

20% Lifetime Recurring Commission

Every person you refer earns you 20% of their spend — forever. If they spend $500/mo on GPUs, you get $100/mo passive income. 10 referrals at $500 = $5,000/mo. No caps. No expiry. Track it all at your referral dashboard.

⚡

World's Largest Serverless GPU Fleet

Access 100,000+ GPUs across 30+ data centers globally. RTX 3080 ($0.17/hr) to H100 ($4.50/hr). Sub-second cold starts. Per-second billing. Auto-scale from 0 to 1000+ workers. No reserved instances needed.

🤗

Native Hugging Face Integration

Deploy any HF model ID directly. Auto-detects architecture, quantization (AWQ, GPTQ, GGUF), and required VRAM. OpenAI-compatible API endpoints. Built-in Flash Attention, vLLM, TGI, and custom Docker support.

💎

Spot Instances: Save 50-70%

Bid on spare capacity. RTX 3090 at $0.11/hr (vs $0.22), A100 40GB at $0.55/hr (vs $1.10). Perfect for batch inference, fine-tuning, and fault-tolerant workloads. Automatic fallback to on-demand.

🛡️

Enterprise-Grade Security & Compliance

SOC 2 Type II, HIPAA-ready, GDPR compliant. Private networking, VPC peering, custom VPCs. End-to-end encryption. Team workspaces with RBAC. Audit logs. Dedicated support SLAs.

🚀

One-Click Fine-Tuning & Training

Launch LoRA/QLoRA fine-tunes on any HF model. Multi-node distributed training with NCCL. Pre-configured Axolotl, Unsloth, HuggingFace Trainer templates. Checkpoint to HF Hub automatically.

🌐

Global Edge & CDN Integration

Deploy inference endpoints at edge locations worldwide. Cloudflare Workers integration. <100ms latency to 95% of internet users. Custom domains, SSL, rate limiting, auth built-in.

Already a RunPod User? Maximize Your Earnings

Log into your referral dashboard to get your personal link, track clicks, signups, conversions, and pending/paid commissions in real-time. Share your link on GitHub, Discord, Twitter, blogs, YouTube — every deploy earns you back. Open Referral Dashboard →