Phi 3 Medium 128k Instruct — Hardware Requirements & GPU Compatibility
ChatCode
Phi-3-Medium-128K-Instruct is Microsoft's 14-billion-parameter instruction-tuned model in the Phi-3 family, trained on a mix of synthetic data and filtered high-quality web content chosen for reasoning density, then post-trained with supervised fine-tuning and direct preference optimization for instruction-following and safety. It is the long-context variant of Phi-3-Medium, alongside a 4K-context sibling, and is aimed at memory- and latency-constrained deployments needing strong code, math, and logical reasoning rather than frontier-scale serving. At 14B parameters, it runs on a single high-end consumer GPU once quantized. Context length is 131,072 tokens. It is released under the MIT license, permitting unrestricted commercial and research use, and was published in May 2024.
12.6K downloads
389 likesSpecifications
- Publisher
- Microsoft
- Family
- Phi 3
- Parameters
- 14.0B
- Architecture
- Phi3ForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 32,064
- Release Date
- 2024-05-07
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does Phi 3 Medium 128k Instruct Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 6.7 GB | 33.1 GB | 5.93 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 6.8 GB | 33.3 GB | 6.11 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 7.5 GB | 34.0 GB | 6.81 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 9.1 GB | 35.5 GB | 8.38 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 10.7 GB | 37.1 GB | 9.95 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 12.2 GB | 38.7 GB | 11.52 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 14.7 GB | 41.1 GB | 13.96 GB | 8-bit quantization, near-lossless |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Phi 3 Medium 128k Instruct?
Q4_K_M · 9.1 GBPhi 3 Medium 128k Instruct (Q4_K_M) requires 9.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 12+ GB is recommended. Using the full 131K context window can add up to 26.4 GB, bringing total usage to 35.5 GB. 40 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080 Ti.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run Phi 3 Medium 128k Instruct?
Q4_K_M · 9.1 GB49 devices with unified memory can run Phi 3 Medium 128k Instruct, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, iPad Pro M5 13" (16 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download Phi 3 Medium 128k Instruct
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Related Models
Frequently Asked Questions
- How much VRAM does Phi 3 Medium 128k Instruct need?
Phi 3 Medium 128k Instruct requires 9.1 GB of VRAM at Q4_K_M, or 28.6 GB at BF16. Full 131K context adds up to 26.4 GB (35.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 14.0B × 4.8 bits ÷ 8 = 8.4 GB
KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 27.1 GB (at full 131K context)
VRAM usage by quantization
Q4_K_M9.1 GBQ4_K_M + full context35.5 GB- Can NVIDIA GeForce RTX 4090 run Phi 3 Medium 128k Instruct?
Yes, at Q8_0 (14.7 GB) or lower. Higher quantizations like BF16 (28.6 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Phi 3 Medium 128k Instruct?
For Phi 3 Medium 128k Instruct, Q4_K_M (9.1 GB) offers the best balance of quality and VRAM usage. Q4_K_L (9.3 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 4.6 GB.
VRAM requirement by quantization
IQ2_XXS4.6 GBIQ3_S6.7 GBQ3_K_L7.9 GBQ4_K_M ★9.1 GBQ5_K_S10.3 GBBF1628.6 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Phi 3 Medium 128k Instruct on a Mac?
Phi 3 Medium 128k Instruct requires at least 4.6 GB at IQ2_XXS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Phi 3 Medium 128k Instruct locally?
Yes — Phi 3 Medium 128k Instruct can run locally on consumer hardware. At Q4_K_M quantization it needs 9.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Phi 3 Medium 128k Instruct?
At Q4_K_M, Phi 3 Medium 128k Instruct can reach ~528 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~72 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 9.1 × 0.65 = ~571 tok/s
Estimated speed at Q4_K_M (9.1 GB)
~571 tok/s~72 tok/s~571 tok/s~528 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Phi 3 Medium 128k Instruct?
At Q4_K_M, the download is about 8.38 GB. The full-precision BF16 version is 27.92 GB. The smallest option (IQ2_XXS) is 3.84 GB.
- Which GPUs can run Phi 3 Medium 128k Instruct?
40 consumer GPUs can run Phi 3 Medium 128k Instruct at Q4_K_M (9.1 GB). Top options include AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 6900 XT, AMD Radeon RX 6700 XT. 26 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Phi 3 Medium 128k Instruct?
52 devices with unified memory can run Phi 3 Medium 128k Instruct at Q4_K_M (9.1 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.