Evo2 1B Base — Hardware Requirements & GPU Compatibility
Chat
Evo2 1B Base is a 1.1B-parameter open language model from Aquiles-ai. It supports a context window of up to 8,192 tokens. At BF16 it needs about 2.44 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 8K)Best on 24 GB (BF16 · ~269 tok/s · 8K)Macs from 8 GB (BF16 · ~29 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Evo2 1B Base
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/Evo2-1B-Base --max-model-len 8192vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (8 GB headroom) · BF16
- Generation speed
- ~243 tok/s
- generation speed
- Cost per 1M output tokens
- $0.14
- per 1M output tokens
How Much VRAM Does Evo2 1B Base Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 2.4 GB | — | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 8K context · ~269 tok/s |
Selected BF16
Brain floating point 163.1GBat 8K context
- Weights
- 1.9 GB
- KV cache
- 0.8 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 20.9 GB free · ~269 tok/s
≥50 tok/s needs ≥188 GB/s · RTX 5090 ~477, RTX 3090 Ti ~269
Which Hardware Can Run Evo2 1B Base?
BF16 · 2.4 GBEvo2 1B Base (BF16) requires 2.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Evo2 1B Base, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 4.9 GB free · up to 8K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~203Simulate output on RTX 3080RTX 2080 Ti~164Simulate output on RTX 2080 TiRTX 3070 Ti~162Simulate output on RTX 3070 TiM3*8 GB~29Simulate output on iMac 24" M3 (8 GB)Orin Nano~27Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~20Simulate output on iPhone 1720 GB
fits · 16.9 GB free · up to 8K ctx
1 GPU
RX 7900 XT~197Simulate output on RX 7900 XT32–40 GB
fits · 28.9 GB free · up to 8K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~477Simulate output on RTX 5090M5 Max36 GB~132Simulate output on Mac Studio M5 Max (36 GB)M532 GB~44Simulate output on MacBook Air 13" M5 (32 GB)Orin~55Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~36Simulate 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 |
|---|---|---|---|---|
| MiniCPM5 1BOpenBMB | — | 1.3 GB | ~662 | same size |
| TinyLlama 1.1B Chat v1.0TinyLlama | — | 1 GB | ~649 | same size |
| LLaMA3.1 8B Instruct DFlash UltraChatz-lab | — | 2.7 GB | ~269 | same size |
| LFM2.5 1.2B ThinkingLiquid AI | — | 1.2 GB | ~612 | same size |
| Vaultgemma 1BGoogle | — | 3.7 GB | ~286 | same size |
| LFM2 1.2BLiquid AI | — | 1.2 GB | ~612 | same size |
Specifications
- Publisher
- Aquiles-ai
- Parameters
- 1.1B
- Architecture
- Evo2ForCausalLM
- Context Length
- 8,192 tokens
- Vocabulary Size
- 512
- Release Date
- 2026-09-14
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Evo2 1B Base need?
Evo2 1B Base requires 2.4 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 1.1B × 16 bits ÷ 8 = 2.2 GB
KV Cache + Overhead ≈ 0.2 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 1B Base on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run Evo2 1B Base. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 2.4 GB of usable unified memory (RAM minus macOS overhead).
Can I run Evo2 1B Base locally?
Yes — Evo2 1B Base can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Evo2 1B Base?
At BF16, Evo2 1B Base can reach ~1967 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~269 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 ÷ 2.44 × 0.65 = ~2131 tok/s
Estimated speed at BF16 (2.4 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Evo2 1B Base?
At BF16, the download is about 2.22 GB.
Which GPUs can run Evo2 1B Base?
52 consumer GPUs can run Evo2 1B Base at BF16. 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 Evo2 1B Base?
163 devices with unified memory can run Evo2 1B Base at BF16 (2.4 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.