Aragpt2 Base — Hardware Requirements & GPU Compatibility
Chat
Aragpt2 Base is a 148M-parameter open language model from aubmindlab. It supports a context window of up to 1,024 tokens. At Q4_K_M it needs about 0.10 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)Best on 24 GB (Q4_K_M · ~6552 tok/s)Macs from 8 GB (Q4_K_M · ~717 tok/s)
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Aragpt2 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 aubmindlab/aragpt2-base --max-model-len 1024vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3060 12GB (11 GB headroom) · Q4_K_M
- Generation speed
- ~2340 tok/s
- generation speed
- Cost per 1M output tokens
- $0.0073
- per 1M output tokens
How Much VRAM Does Aragpt2 Base Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.1 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: — context · ~9360 tok/s | |
| 0.1 GB | — | 3-bit medium — 3-bit medium quantization | Fits: — context · ~8190 tok/s | |
| 0.1 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: — context · ~6552 tok/s | |
| 0.1 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: — context · ~5460 tok/s | |
| 0.1 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Fits: — context · ~5040 tok/s | |
| 0.2 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: — context · ~4095 tok/s | |
| 0.3 GB | — | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: — context · ~2048 tok/s |
Selected Q4_K_M
4-bit medium quantization0.1GBat 1K context
- Weights
- 0.1 GB
- KV cache
- 0.0 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 23.9 GB free · ~6552 tok/s
≥50 tok/s needs ≥8 GB/s · RTX 5090 ~11648, RTX 3090 Ti ~6552
Which Hardware Can Run Aragpt2 Base?
Q4_K_M · 0.1 GBAragpt2 Base (Q4_K_M) requires 0.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ 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 Aragpt2 Base, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 7.9 GB free · up to — ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~4942Simulate output on RTX 3080RTX 2080 Ti~4004Simulate output on RTX 2080 TiRTX 3070 Ti~3954Simulate output on RTX 3070 TiM3*8 GB~717Simulate output on iMac 24" M3 (8 GB)Orin Nano~663Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~477Simulate output on iPhone 1720 GB
fits · 19.9 GB free · up to — ctx
1 GPU
RX 7900 XT~4800Simulate output on RX 7900 XT32–40 GB
fits · 31.9 GB free · up to — ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~11648Simulate output on RTX 5090M5 Max36 GB~3220Simulate output on Mac Studio M5 Max (36 GB)M532 GB~1075Simulate output on MacBook Air 13" M5 (32 GB)Orin~1331Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~878Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Specifications
- Publisher
- aubmindlab
- Parameters
- 148M
- Architecture
- GPT2LMHeadModel
- Context Length
- 1,024 tokens
- Vocabulary Size
- 64,000
- Release Date
- 2022-03-02
Frequently Asked Questions
How much VRAM does Aragpt2 Base need?
Aragpt2 Base requires 0.1 GB of VRAM at Q4_K_M, or 0.3 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 148M × 4.8 bits ÷ 8 = 0.1 GB
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
What's the best quantization for Aragpt2 Base?
For Aragpt2 Base, Q4_K_M (0.1 GB) offers the best balance of quality and VRAM usage. Q5_K_M (0.1 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 0.1 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Aragpt2 Base on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Aragpt2 Base. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 0.1 GB of usable unified memory (RAM minus macOS overhead).
Can I run Aragpt2 Base locally?
Yes — Aragpt2 Base can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Aragpt2 Base?
At Q4_K_M, Aragpt2 Base can reach ~48000 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~6552 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 ÷ 0.1 × 0.65 = ~52000 tok/s
Estimated speed at Q4_K_M (0.1 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Aragpt2 Base?
At Q4_K_M, the download is about 0.09 GB. The full-precision BF16 version is 0.30 GB. The smallest option (Q2_K) is 0.06 GB.
Which GPUs can run Aragpt2 Base?
52 consumer GPUs can run Aragpt2 Base 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 Aragpt2 Base?
163 devices with unified memory can run Aragpt2 Base at Q4_K_M (0.1 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.