Puro 2B Base — Hardware Requirements & GPU Compatibility
Chat
Puro 2B Base is a 2.0B-parameter open language model from thu-pacman. It supports a context window of up to 4,096 tokens. At Q4_K_M it needs about 1.75 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 · 4K)Best on 24 GB (Q4_K_M · ~374 tok/s · 4K)Macs from 8 GB (Q4_K_M · ~41 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Puro 2B Base
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve thu-pacman/Puro-2B-Base --max-model-len 4096vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (10 GB headroom) · Q4_K_M
- Generation speed
- ~134 tok/s
- generation speed
- Cost per 1M output tokens
- $0.17
- per 1M output tokens
How Much VRAM Does Puro 2B Base Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.4 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 4K context · ~468 tok/s | |
| 1.5 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 4K context · ~428 tok/s | |
| 1.8 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 4K context · ~374 tok/s | |
| 2.0 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 4K context · ~331 tok/s | |
| 2.2 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Fits: 4K context · ~297 tok/s | |
| 2.6 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 4K context · ~255 tok/s | |
| 4.6 GB | — | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 4K context · ~142 tok/s |
Selected Q4_K_M
4-bit medium quantization2.0GBat 4K context
- Weights
- 1.2 GB
- KV cache
- 0.5 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 22.0 GB free · ~374 tok/s
≥50 tok/s needs ≥134 GB/s · RTX 5090 ~666, RTX 3090 Ti ~374
Which Hardware Can Run Puro 2B Base?
Q4_K_M · 1.8 GBPuro 2B Base (Q4_K_M) requires 1.8 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 4K context window can add up to 0.2 GB, bringing total usage to 2.0 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Puro 2B Base, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 6.0 GB free · up to 4K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~282Simulate output on RTX 3080RTX 2080 Ti~229Simulate output on RTX 2080 TiRTX 3070 Ti~226Simulate output on RTX 3070 TiM3*8 GB~41Simulate output on iMac 24" M3 (8 GB)Orin Nano~38Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~27Simulate output on iPhone 1720 GB
fits · 18.0 GB free · up to 4K ctx
1 GPU
RX 7900 XT~274Simulate output on RX 7900 XT32–40 GB
fits · 30.0 GB free · up to 4K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~666Simulate output on RTX 5090M5 Max36 GB~184Simulate output on Mac Studio M5 Max (36 GB)M532 GB~61Simulate output on MacBook Air 13" M5 (32 GB)Orin~76Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~50Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
4| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3 VL 2B InstructAlibaba | — | 3.5 GB | ~362 | same size |
| Gemma 3n E2B IT Litert LmGoogle | — | 3.1 GB | ~496 | same size |
| MiniCPM 2B Sft BF16OpenBMB | — | 3 GB | ~291 | same size |
| Nemotron Labs Audex 2BNVIDIA | — | 6.1 GB | ~149 | same size |
Specifications
- Publisher
- thu-pacman
- Parameters
- 2.0B
- Architecture
- Qwen3ForCausalLM
- Context Length
- 4,096 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2026-08-16
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Puro 2B Base need?
Puro 2B Base requires 1.8 GB of VRAM at Q4_K_M, or 4.6 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 2.0B × 4.8 bits ÷ 8 = 1.2 GB
KV Cache + Overhead ≈ 0.6 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 ≈ 0.8 GB (at full 4K context)
VRAM usage by quantization
What's the best quantization for Puro 2B Base?
For Puro 2B Base, Q4_K_M (1.8 GB) offers the best balance of quality and VRAM usage. Q5_K_M (2.0 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Puro 2B Base on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Puro 2B Base. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.8 GB of usable unified memory (RAM minus macOS overhead).
Can I run Puro 2B Base locally?
Yes — Puro 2B Base can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Puro 2B Base?
At Q4_K_M, Puro 2B Base can reach ~2743 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~374 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 ÷ 1.75 × 0.65 = ~2971 tok/s
Estimated speed at Q4_K_M (1.8 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Puro 2B Base?
At Q4_K_M, the download is about 1.22 GB. The full-precision BF16 version is 4.06 GB. The smallest option (Q2_K) is 0.86 GB.
Which GPUs can run Puro 2B Base?
52 consumer GPUs can run Puro 2B 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 Puro 2B Base?
163 devices with unified memory can run Puro 2B Base at Q4_K_M (1.8 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.