MiniMax M3 EAGLE3 GQA — Hardware Requirements & GPU Compatibility
Chat
MiniMax M3 EAGLE3 GQA is a 3.1B-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 2.15 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 · 1M)Best on 24 GB (Q4_K_M · ~305 tok/s · 1M)Macs from 8 GB (Q4_K_M · ~33 tok/s)
MIT
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run MiniMax M3 EAGLE3 GQA
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve Inferact/MiniMax-M3-EAGLE3-GQA --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
- ~109 tok/s
- generation speed
- Cost per 1M output tokens
- $0.18
- per 1M output tokens
How Much VRAM Does MiniMax M3 EAGLE3 GQA Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.6 GB | 1.7 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 1M context · ~407 tok/s | |
| 1.8 GB | 1.9 GB | 3-bit medium — 3-bit medium quantization | Fits: 1M context · ~364 tok/s | |
| 2.1 GB | 2.2 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 1M context · ~305 tok/s | |
| 2.5 GB | 2.5 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 1M context · ~263 tok/s | |
| 2.8 GB | 2.9 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 1M context · ~231 tok/s | |
| 3.4 GB | 3.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 1M context · ~194 tok/s | |
| 6.5 GB | 6.5 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 1M context · ~102 tok/s |
Selected Q4_K_M
4-bit medium quantization2.2GBat 16K context
- Weights
- 1.9 GB
- KV cache
- 0.0 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 21.8 GB free · ~305 tok/s
≥50 tok/s needs ≥165 GB/s · RTX 5090 ~542, RTX 3090 Ti ~305
Which Hardware Can Run MiniMax M3 EAGLE3 GQA?
Q4_K_M · 2.1 GBMiniMax M3 EAGLE3 GQA (Q4_K_M) requires 2.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. Using the full 1049K context window can add up to 1.6 GB, bringing total usage to 3.8 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 GQA, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 5.8 GB free · up to 1M ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~230Simulate output on RTX 3080RTX 2080 Ti~186Simulate output on RTX 2080 TiRTX 3070 Ti~184Simulate output on RTX 3070 TiM3*8 GB~33Simulate output on iMac 24" M3 (8 GB)Orin Nano~31Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~22Simulate output on iPhone 1720 GB
fits · 17.8 GB free · up to 1M ctx
1 GPU
RX 7900 XT~223Simulate output on RX 7900 XT32–40 GB
fits · 29.8 GB free · up to 1M ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~542Simulate output on RTX 5090M5 Max36 GB~150Simulate output on Mac Studio M5 Max (36 GB)M532 GB~50Simulate output on MacBook Air 13" M5 (32 GB)Orin~62Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~41Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to MiniMax M3 EAGLE3 GQA
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 |
| SmolLM3 3BHugging Face | — | 3.4 GB | ~285 | same size |
| Llama 3.2 3B InstructMeta | — | 4.1 GB | ~309 | same size |
| AI21 Jamba Reasoning 3BAI21 Labs | — | 2.3 GB | ~291 | same size |
| Qwen2.5 3B InstructAlibaba | — | 2.8 GB | ~294 | same size |
| Quasar 3B A1B Previewsilx-ai | — | 8.4 GB | ~167 | same size |
Specifications
- Publisher
- Inferact
- Family
- MiniMax
- Parameters
- 3.1B
- Architecture
- LlamaForCausalLMEagle3
- Context Length
- 1,048,576 tokens
- Vocabulary Size
- 200,064
- Release Date
- 2026-07-15
- License
- MIT
Frequently Asked Questions
How much VRAM does MiniMax M3 EAGLE3 GQA need?
MiniMax M3 EAGLE3 GQA requires 2.1 GB of VRAM at Q4_K_M, or 6.5 GB at BF16. Full 1049K context adds up to 1.6 GB (3.8 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 3.1B × 4.8 bits ÷ 8 = 1.8 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 ≈ 2 GB (at full 1049K context)
VRAM usage by quantization
What's the best quantization for MiniMax M3 EAGLE3 GQA?
For MiniMax M3 EAGLE3 GQA, Q4_K_M (2.1 GB) offers the best balance of quality and VRAM usage. Q5_K_M (2.5 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.6 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run MiniMax M3 EAGLE3 GQA on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run MiniMax M3 EAGLE3 GQA. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 2.1 GB of usable unified memory (RAM minus macOS overhead).
Can I run MiniMax M3 EAGLE3 GQA locally?
Yes — MiniMax M3 EAGLE3 GQA can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is MiniMax M3 EAGLE3 GQA?
At Q4_K_M, MiniMax M3 EAGLE3 GQA can reach ~2233 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~305 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 ÷ 2.15 × 0.65 = ~2419 tok/s
Estimated speed at Q4_K_M (2.1 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 GQA?
At Q4_K_M, the download is about 1.84 GB. The full-precision BF16 version is 6.15 GB. The smallest option (Q2_K) is 1.31 GB.
Which GPUs can run MiniMax M3 EAGLE3 GQA?
52 consumer GPUs can run MiniMax M3 EAGLE3 GQA 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 GQA?
163 devices with unified memory can run MiniMax M3 EAGLE3 GQA at Q4_K_M (2.1 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.