ERNIE 4.5 0.3B PT — Hardware Requirements & GPU Compatibility
Chat
ERNIE 4.5 0.3B PT is a 361M-parameter open language model from Baidu in the ERNIE family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 0.54 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 · 128K)Best on 24 GB (Q4_K_M · ~1213 tok/s · 128K)Macs from 8 GB (Q4_K_M · ~133 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run ERNIE 4.5 0.3B PT
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve baidu/ERNIE-4.5-0.3B-PT --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (11 GB headroom) · Q4_K_M
- Generation speed
- ~433 tok/s
- generation speed
- Cost per 1M output tokens
- $0.053
- per 1M output tokens
How Much VRAM Does ERNIE 4.5 0.3B PT Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.5 GB | 0.8 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 128K context · ~1394 tok/s | |
| 0.5 GB | 0.8 GB | 3-bit medium — 3-bit medium quantization | Fits: 128K context · ~1337 tok/s | |
| 0.5 GB | 0.8 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 128K context · ~1213 tok/s | |
| 0.6 GB | 0.9 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 128K context · ~1130 tok/s | |
| 0.6 GB | 0.9 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 128K context · ~1057 tok/s | |
| 0.7 GB | 1 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 128K context · ~964 tok/s | |
| 1.0 GB | 1.3 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 128K context · ~630 tok/s |
Selected Q4_K_M
4-bit medium quantization0.7GBat 16K context
- Weights
- 0.2 GB
- KV cache
- 0.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 23.3 GB free · ~1213 tok/s
≥50 tok/s needs ≥41 GB/s · RTX 5090 ~2157, RTX 3090 Ti ~1213
Which Hardware Can Run ERNIE 4.5 0.3B PT?
Q4_K_M · 0.5 GBERNIE 4.5 0.3B PT (Q4_K_M) requires 0.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. Using the full 131K context window can add up to 1.2 GB, bringing total usage to 1.7 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run ERNIE 4.5 0.3B PT, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 7.3 GB free · up to 128K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~915Simulate output on RTX 3080RTX 2080 Ti~742Simulate output on RTX 2080 TiRTX 3070 Ti~732Simulate output on RTX 3070 TiM3*8 GB~133Simulate output on iMac 24" M3 (8 GB)Orin Nano~123Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~88Simulate output on iPhone 1720 GB
fits · 19.3 GB free · up to 128K ctx
1 GPU
RX 7900 XT~889Simulate output on RX 7900 XT32–40 GB
fits · 31.3 GB free · up to 128K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~2157Simulate output on RTX 5090M5 Max36 GB~596Simulate output on Mac Studio M5 Max (36 GB)M532 GB~199Simulate output on MacBook Air 13" M5 (32 GB)Orin~247Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~163Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to ERNIE 4.5 0.3B PT
ERNIE family · 6 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Granite 4.0 350MIBM | — | 1 GB | ~1150 | same size |
| SmolLM 360MHugging Face | — | 0.6 GB | ~1092 | same size |
| LFM2.5 350MLiquid AI | — | 0.8 GB | ~1130 | same size |
| Opt 350MMeta | — | 0.8 GB | ~851 | same size |
| Codegen 350M MonoSalesforce | — | 0.8 GB | ~851 | same size |
| Gpt2 MediumOpenAI | — | 0.3 GB | ~2621 | same size |
Specifications
- Publisher
- Baidu
- Family
- ERNIE
- Parameters
- 361M
- Architecture
- Ernie4_5ForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 103,424
- Release Date
- 2025-06-28
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does ERNIE 4.5 0.3B PT need?
ERNIE 4.5 0.3B PT requires 0.5 GB of VRAM at Q4_K_M, or 1.0 GB at BF16. Full 131K context adds up to 1.2 GB (1.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 361M × 4.8 bits ÷ 8 = 0.2 GB
KV Cache + Overhead ≈ 0.3 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.
KV Cache + Overhead ≈ 1.5 GB (at full 131K context)
VRAM usage by quantization
What's the best quantization for ERNIE 4.5 0.3B PT?
For ERNIE 4.5 0.3B PT, Q4_K_M (0.5 GB) offers the best balance of quality and VRAM usage. Q5_K_M (0.6 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 0.5 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run ERNIE 4.5 0.3B PT on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run ERNIE 4.5 0.3B PT. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 0.5 GB of usable unified memory (RAM minus macOS overhead).
Can I run ERNIE 4.5 0.3B PT locally?
Yes — ERNIE 4.5 0.3B PT can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is ERNIE 4.5 0.3B PT?
At Q4_K_M, ERNIE 4.5 0.3B PT can reach ~8889 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1213 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 ÷ 0.54 × 0.65 = ~9630 tok/s
Estimated speed at Q4_K_M (0.5 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of ERNIE 4.5 0.3B PT?
At Q4_K_M, the download is about 0.22 GB. The full-precision BF16 version is 0.72 GB. The smallest option (Q2_K) is 0.15 GB.
Which GPUs can run ERNIE 4.5 0.3B PT?
52 consumer GPUs can run ERNIE 4.5 0.3B PT 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 ERNIE 4.5 0.3B PT?
163 devices with unified memory can run ERNIE 4.5 0.3B PT at Q4_K_M (0.5 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.