Evo2 7B — Hardware Requirements & GPU Compatibility
Chat
Evo2 7B is a 6.6B-parameter open language model from Aquiles-ai. It supports a context window of up to 1,048,576 tokens. At BF16 it needs about 14.48 GB of VRAM — see which GPUs and Macs can run it below.
Runs well on a 24 GB GPU
Runs from 16 GB (BF16 · 8K)Best on 24 GB (BF16 · ~45 tok/s · 32K)Macs from 18 GB (BF16 · ~7 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Evo2 7B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve Aquiles-ai/Evo2-7B --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3090 (24 GB) (7 GB headroom) · BF16
- Generation speed
- ~42 tok/s
- generation speed
- Cost per 1M output tokens
- $1.31
- per 1M output tokens
How Much VRAM Does Evo2 7B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 14.5 GB | 19.7 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~45 tok/s |
Selected BF16
Brain floating point 1616.9GBat 16K context
- Weights
- 13.8 GB
- KV cache
- 2.8 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 7.1 GB free · ~45 tok/s
≥50 tok/s needs ≥1.11 TB/s · RTX 5090 ~80
Which Hardware Can Run Evo2 7B?
BF16 · 14.5 GBEvo2 7B (BF16) requires 14.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 19+ GB is recommended. 26 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 5080. 124 devices with unified memory can run Evo2 7B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M5 Pro (24 GB).
20 GB
fits · 3.1 GB free · up to 32K ctx
1 GPU
RX 7900 XT~33Simulate output on RX 7900 XT32–40 GB
fits · 15.1 GB free · up to 64K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~80Simulate output on RTX 5090M5 Max36 GB~22Simulate output on Mac Studio M5 Max (36 GB)M532 GB~7Simulate output on MacBook Air 13" M5 (32 GB)Orin~9Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~6Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Llava 1.5 7B HFllava-hf | — | 5 GB | ~141 | same size |
| Chatglm3 6BZ.ai | — | 5.2 GB | ~159 | same size |
| Baichuan2 7B Basebaichuan-inc | — | 5 GB | ~142 | same size |
| Internlm 7BInternLM | — | 15.4 GB | ~43 | same size |
| Olmo Hybrid 7BAllen AI | — | 22.4 GB | ~43 | same size |
| Granite 4.0 H TinyIBM | — | 5.8 GB | ~271 | same size |
Specifications
- Publisher
- Aquiles-ai
- Parameters
- 6.6B
- Architecture
- Evo2ForCausalLM
- Context Length
- 1,048,576 tokens
- Vocabulary Size
- 512
- Release Date
- 2026-09-14
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Evo2 7B need?
Evo2 7B requires 14.5 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 6.6B × 16 bits ÷ 8 = 13.2 GB
KV Cache + Overhead ≈ 1.3 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.
VRAM usage by quantization
Can I run Evo2 7B on a Mac?
Yes — MacBook Pro 14" M3 Pro (18 GB) and 108 other Macs can run Evo2 7B. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 14.5 GB of usable unified memory (RAM minus macOS overhead).
Can I run Evo2 7B locally?
Yes — Evo2 7B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Evo2 7B?
At BF16, Evo2 7B can reach ~332 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~45 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 ÷ 14.5 × 0.65 = ~359 tok/s
Estimated speed at BF16 (14.5 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Evo2 7B?
At BF16, the download is about 13.16 GB.
Which GPUs can run Evo2 7B?
26 consumer GPUs can run Evo2 7B at BF16. Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3090 Ti, AMD Radeon RX 6800. 7 GPUs have plenty of headroom for comfortable inference.
Which devices can run Evo2 7B?
124 devices with unified memory can run Evo2 7B at BF16 (14.5 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.