PowerMoE 3B — Hardware Requirements & GPU Compatibility
Chat
PowerMoE-3B is IBM Research's 3.4-billion-parameter sparse Mixture-of-Experts language model, built for general text generation, reasoning, and code rather than a specific vision or audio modality. It routes each token to 8 of 40 experts, activating roughly 800 million parameters per token according to IBM, keeping decoding fast even though the full set of experts still has to be held in memory. At this size it fits comfortably on a single mainstream consumer GPU once quantized. Context length is limited to 4,096 tokens. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in August 2024. Its defining feature is the Power learning-rate scheduler IBM used to train it, which the team reports lets an 800-million-active-parameter model match dense models with roughly twice as many active parameters.
919.1K downloads
22 likesSpecifications
- Publisher
- ibm-research
- Parameters
- 3.4B
- Architecture
- GraniteMoeForCausalLM
- Context Length
- 4,096 tokens
- Vocabulary Size
- 49,152
- Release Date
- 2024-08-14
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does PowerMoE 3B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 1.9 GB | 2 GB | 1.43 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 1.9 GB | 2.0 GB | 1.48 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 2.1 GB | 2.2 GB | 1.64 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 2.5 GB | 2.6 GB | 2.02 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 2.8 GB | 3.0 GB | 2.40 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 3.2 GB | 3.4 GB | 2.78 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 3.8 GB | 3.9 GB | 3.37 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 PowerMoE 3B?
Q4_K_M · 2.5 GBPowerMoE 3B (Q4_K_M) requires 2.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. Using the full 4K context window can add up to 0.1 GB, bringing total usage to 2.6 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run PowerMoE 3B?
Q4_K_M · 2.5 GB59 devices with unified memory can run PowerMoE 3B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download PowerMoE 3B
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does PowerMoE 3B need?
PowerMoE 3B requires 2.5 GB of VRAM at Q4_K_M, or 7.2 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 3.4B × 4.8 bits ÷ 8 = 2 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 0.6 GB (at full 4K context)
VRAM usage by quantization
Q4_K_M2.5 GBQ4_K_M + full context2.6 GB- What's the best quantization for PowerMoE 3B?
For PowerMoE 3B, Q4_K_M (2.5 GB) offers the best balance of quality and VRAM usage. Q5_K_S (2.8 GB) provides better quality if you have the VRAM. The smallest option is IQ3_XXS at 1.7 GB.
VRAM requirement by quantization
IQ3_XXS1.7 GBQ3_K_S1.9 GBIQ4_XS2.3 GBQ4_K_M ★2.5 GBQ5_K_S2.8 GBBF167.2 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run PowerMoE 3B on a Mac?
PowerMoE 3B requires at least 1.7 GB at IQ3_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 PowerMoE 3B locally?
Yes — PowerMoE 3B can run locally on consumer hardware. At Q4_K_M quantization it needs 2.5 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is PowerMoE 3B?
At Q4_K_M, PowerMoE 3B can reach ~153 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~354 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 ÷ 2.5 × 0.65 = ~528 tok/s
Estimated speed at Q4_K_M (2.5 GB)
~528 tok/s~354 tok/s~528 tok/s~505 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of PowerMoE 3B?
At Q4_K_M, the download is about 2.02 GB. The full-precision BF16 version is 6.75 GB. The smallest option (IQ3_XXS) is 1.31 GB.
- Which GPUs can run PowerMoE 3B?
52 consumer GPUs can run PowerMoE 3B at Q4_K_M (2.5 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
- Which devices can run PowerMoE 3B?
59 devices with unified memory can run PowerMoE 3B at Q4_K_M (2.5 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.