MiniMax M3 EAGLE3 — Hardware Requirements & GPU Compatibility
Chat
MiniMax M3 EAGLE3 is a 3.3B-parameter open language model from Inferact in the MiniMax family. It supports a context window of up to 1,048,576 tokens. At Q4_K_M it needs about 2.31 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 128K)Best on 24 GB (Q4_K_M · ~284 tok/s · 512K)Macs from 8 GB (Q4_K_M · ~31 tok/s)
MIT
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run MiniMax M3 EAGLE3
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve Inferact/MiniMax-M3-EAGLE3 --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (9 GB headroom) · Q4_K_M
- Generation speed
- ~101 tok/s
- generation speed
- Cost per 1M output tokens
- $0.19
- per 1M output tokens
How Much VRAM Does MiniMax M3 EAGLE3 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.7 GB | 2.5 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 512K context · ~377 tok/s | |
| 1.9 GB | 2.7 GB | 3-bit medium — 3-bit medium quantization | Fits: 512K context · ~338 tok/s | |
| 2.3 GB | 3.1 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 512K context · ~284 tok/s | |
| 2.7 GB | 3.4 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 512K context · ~245 tok/s | |
| 3.0 GB | 3.8 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 512K context · ~216 tok/s | |
| 3.6 GB | 4.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 512K context · ~182 tok/s | |
| 6.9 GB | 7.6 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 512K context · ~95 tok/s |
Selected Q4_K_M
4-bit medium quantization2.7GBat 16K context
- Weights
- 2.0 GB
- KV cache
- 0.4 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 21.3 GB free · ~284 tok/s
≥50 tok/s needs ≥178 GB/s · RTX 5090 ~504, RTX 3090 Ti ~284
Which Hardware Can Run MiniMax M3 EAGLE3?
Q4_K_M · 2.3 GBMiniMax M3 EAGLE3 (Q4_K_M) requires 2.3 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 1049K context window can add up to 25.7 GB, bringing total usage to 28.0 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run MiniMax M3 EAGLE3, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 5.3 GB free · up to 128K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~214Simulate output on RTX 3080RTX 2080 Ti~173Simulate output on RTX 2080 TiRTX 3070 Ti~171Simulate output on RTX 3070 TiM3*8 GB~31Simulate output on iMac 24" M3 (8 GB)Orin Nano~29Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~21Simulate output on iPhone 1720 GB
fits · 17.3 GB free · up to 512K ctx
1 GPU
RX 7900 XT~208Simulate output on RX 7900 XT32–40 GB
fits · 29.3 GB free · up to 1M ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~504Simulate output on RTX 5090M5 Max36 GB~139Simulate output on Mac Studio M5 Max (36 GB)M532 GB~47Simulate output on MacBook Air 13" M5 (32 GB)Orin~58Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~38Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to MiniMax M3 EAGLE3
MiniMax family · 9 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| D1 3BLiquid AI | — | 2.6 GB | ~285 | same size |
| Granite 4.0 MicroIBM | — | 3.7 GB | ~261 | same size |
| SmolLM3 3BHugging Face | — | 3.4 GB | ~285 | same size |
| Deepseek Vl2 TinyDeepSeek | — | 9.4 GB | ~152 | same size |
| Llama 3.2 3B InstructMeta | — | 4.1 GB | ~309 | same size |
| AI21 Jamba Reasoning 3BAI21 Labs | — | 2.3 GB | ~291 | same size |
Specifications
- Publisher
- Inferact
- Family
- MiniMax
- Parameters
- 3.3B
- Architecture
- LlamaForCausalLMEagle3
- Context Length
- 1,048,576 tokens
- Vocabulary Size
- 200,064
- Release Date
- 2026-06-02
- License
- MIT
Frequently Asked Questions
How much VRAM does MiniMax M3 EAGLE3 need?
MiniMax M3 EAGLE3 requires 2.3 GB of VRAM at Q4_K_M, or 6.9 GB at BF16. Full 1049K context adds up to 25.7 GB (28.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 3.3B × 4.8 bits ÷ 8 = 2 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 26 GB (at full 1049K context)
VRAM usage by quantization
What's the best quantization for MiniMax M3 EAGLE3?
For MiniMax M3 EAGLE3, Q4_K_M (2.3 GB) offers the best balance of quality and VRAM usage. Q5_K_M (2.7 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.7 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run MiniMax M3 EAGLE3 on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run MiniMax M3 EAGLE3. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 2.3 GB of usable unified memory (RAM minus macOS overhead).
Can I run MiniMax M3 EAGLE3 locally?
Yes — MiniMax M3 EAGLE3 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is MiniMax M3 EAGLE3?
At Q4_K_M, MiniMax M3 EAGLE3 can reach ~2078 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~284 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 ÷ 2.31 × 0.65 = ~2251 tok/s
Estimated speed at Q4_K_M (2.3 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of MiniMax M3 EAGLE3?
At Q4_K_M, the download is about 1.96 GB. The full-precision BF16 version is 6.53 GB. The smallest option (Q2_K) is 1.39 GB.
Which GPUs can run MiniMax M3 EAGLE3?
52 consumer GPUs can run MiniMax M3 EAGLE3 at Q4_K_M. 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 MiniMax M3 EAGLE3?
163 devices with unified memory can run MiniMax M3 EAGLE3 at Q4_K_M (2.3 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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.