Phi 3.5 MoE Instruct — Hardware Requirements & GPU Compatibility
ChatCode
Phi 3.5 MoE Instruct is a 41.9B-parameter open language model from Microsoft in the Phi 3 family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 25.69 GB of VRAM — see which GPUs and Macs can run it below.
159.5K downloads
574 likesSpecifications
- Publisher
- Microsoft
- Family
- Phi 3
- Parameters
- 41.9B
- Architecture
- PhiMoEForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 32,064
- Release Date
- 2024-08-17
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does Phi 3.5 MoE Instruct Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 18.4 GB | 35.3 GB | 17.80 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 18.9 GB | 35.8 GB | 18.32 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 21.0 GB | 37.9 GB | 20.41 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 21.5 GB | 38.4 GB | 20.94 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 25.7 GB | 42.6 GB | 25.12 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 30.4 GB | 47.3 GB | 29.83 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 35.1 GB | 52.0 GB | 34.55 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 42.4 GB | 59.4 GB | 41.87 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 3.5 MoE Instruct?
Q4_K_M · 25.7 GBPhi 3.5 MoE Instruct (Q4_K_M) requires 25.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 34+ GB is recommended. Using the full 131K context window can add up to 16.9 GB, bringing total usage to 42.6 GB. 1 GPU can run it, including NVIDIA GeForce RTX 5090.
All compatible consumer-level GPUs are running near their VRAM limit. You may also want to consider professional GPUs (e.g., NVIDIA A100, H100) which offer significantly more VRAM. For more headroom and better throughput, consider a multi-GPU configuration with tensor parallelism (supported by tools like vLLM, llama.cpp, or text-generation-inference).
Decent
— Enough VRAM, may be tightWhich Devices Can Run Phi 3.5 MoE Instruct?
Q4_K_M · 25.7 GB32 devices with unified memory can run Phi 3.5 MoE Instruct, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio M4 Max (36 GB).
Runs great
— Plenty of headroomWhere to Download Phi 3.5 MoE 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 3.5 MoE Instruct need?
Phi 3.5 MoE Instruct requires 25.7 GB of VRAM at Q4_K_M, or 84.3 GB at BF16. Full 131K context adds up to 16.9 GB (42.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 41.9B × 4.8 bits ÷ 8 = 25.1 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 17.5 GB (at full 131K context)
VRAM usage by quantization
Q4_K_M25.7 GBQ4_K_M + full context42.6 GB- Can NVIDIA GeForce RTX 4090 run Phi 3.5 MoE Instruct?
Yes, at IQ4_XS (23.1 GB) or lower. Higher quantizations like Q4_1 (24.1 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Phi 3.5 MoE Instruct?
For Phi 3.5 MoE Instruct, Q4_K_M (25.7 GB) offers the best balance of quality and VRAM usage. Q4_K_L (26.2 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 12.1 GB.
VRAM requirement by quantization
IQ2_XXS12.1 GBQ3_K_S18.9 GBQ4_124.1 GBQ4_K_M ★25.7 GBQ5_026.7 GBBF1684.3 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Phi 3.5 MoE Instruct on a Mac?
Phi 3.5 MoE Instruct requires at least 12.1 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 3.5 MoE Instruct locally?
Yes — Phi 3.5 MoE Instruct can run locally on consumer hardware. At Q4_K_M quantization it needs 25.7 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Phi 3.5 MoE Instruct?
At Q4_K_M, Phi 3.5 MoE Instruct can reach ~171 tok/s on AMD Instinct MI350X. 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 ÷ 25.7 × 0.65 = ~202 tok/s
Estimated speed at Q4_K_M (25.7 GB)
~202 tok/s~202 tok/s~171 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Phi 3.5 MoE Instruct?
At Q4_K_M, the download is about 25.12 GB. The full-precision BF16 version is 83.75 GB. The smallest option (IQ2_XXS) is 11.52 GB.
- Which GPUs can run Phi 3.5 MoE Instruct?
1 consumer GPU can run Phi 3.5 MoE Instruct at Q4_K_M (25.7 GB). Top options include NVIDIA GeForce RTX 5090.
- Which devices can run Phi 3.5 MoE Instruct?
35 devices with unified memory can run Phi 3.5 MoE Instruct at Q4_K_M (25.7 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (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.