EuroMoE 2.6B A0.6B 2512 — Hardware Requirements & GPU Compatibility
Chat
EuroMoE 2.6B A0.6B 2512 is a 2.6B-parameter open language model from utter-project. It supports a context window of up to 4,096 tokens. At BF16 it needs about 5.57 GB of VRAM — see which GPUs and Macs can run it below.
1.5K downloads
8 likesSpecifications
- Publisher
- utter-project
- Parameters
- 2.6B
- Architecture
- MixtralForCausalLM
- Context Length
- 4,096 tokens
- Vocabulary Size
- 128,000
- Release Date
- 2026-02-06
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does EuroMoE 2.6B A0.6B 2512 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 5.6 GB | 5.6 GB | 5.22 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run EuroMoE 2.6B A0.6B 2512?
BF16 · 5.6 GBEuroMoE 2.6B A0.6B 2512 (BF16) requires 5.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 8+ GB is recommended. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run EuroMoE 2.6B A0.6B 2512?
BF16 · 5.6 GB33 devices with unified memory can run EuroMoE 2.6B A0.6B 2512, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, MacBook Air 13" M3 (8 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does EuroMoE 2.6B A0.6B 2512 need?
EuroMoE 2.6B A0.6B 2512 requires 5.6 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 2.6B × 16 bits ÷ 8 = 5.2 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 0.4 GB (at full 4K context)
VRAM usage by quantization
BF165.6 GBBF16 + full context5.6 GB- Can I run EuroMoE 2.6B A0.6B 2512 on a Mac?
EuroMoE 2.6B A0.6B 2512 requires at least 5.6 GB at BF16, 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 EuroMoE 2.6B A0.6B 2512 locally?
Yes — EuroMoE 2.6B A0.6B 2512 can run locally on consumer hardware. At BF16 quantization it needs 5.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is EuroMoE 2.6B A0.6B 2512?
At BF16, EuroMoE 2.6B A0.6B 2512 can reach ~523 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~118 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 5.6 × 0.55 = ~523 tok/s
Estimated speed at BF16 (5.6 GB)
~523 tok/s~118 tok/s~391 tok/s~324 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of EuroMoE 2.6B A0.6B 2512?
At BF16, the download is about 5.22 GB.
- Which GPUs can run EuroMoE 2.6B A0.6B 2512?
35 consumer GPUs can run EuroMoE 2.6B A0.6B 2512 at BF16 (5.6 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 28 GPUs have plenty of headroom for comfortable inference.
- Which devices can run EuroMoE 2.6B A0.6B 2512?
33 devices with unified memory can run EuroMoE 2.6B A0.6B 2512 at BF16 (5.6 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.