ErniePEUnleashed — Hardware Requirements & GPU Compatibility
Chat
ErniePEUnleashed is a 3.4B-parameter open language model from Kezmark in the ERNIE family. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 2.52 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 · 64K)Best on 24 GB (Q4_K_M · ~260 tok/s · 256K)Macs from 8 GB (Q4_K_M · ~28 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run ErniePEUnleashed
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve Kezmark/ErniePEUnleashed --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 (8 GB headroom) · Q4_K_M
- Generation speed
- ~93 tok/s
- generation speed
- Cost per 1M output tokens
- $0.21
- per 1M output tokens
How Much VRAM Does ErniePEUnleashed Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.9 GB | 4.4 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 256K context · ~341 tok/s | |
| 2.1 GB | 4.6 GB | 3-bit medium — 3-bit medium quantization | Fits: 256K context · ~306 tok/s | |
| 2.5 GB | 5 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 256K context · ~260 tok/s | |
| 2.9 GB | 5.4 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 256K context · ~225 tok/s | |
| 3.3 GB | 5.7 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 128K context · ~199 tok/s | |
| 3.9 GB | 6.3 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 128K context · ~168 tok/s | |
| 7.3 GB | 9.8 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 128K context · ~90 tok/s |
Selected Q4_K_M
4-bit medium quantization3.7GBat 16K context
- Weights
- 2.1 GB
- KV cache
- 1.3 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 20.3 GB free · ~260 tok/s
≥50 tok/s needs ≥194 GB/s · RTX 5090 ~462, RTX 3090 Ti ~260
Which Hardware Can Run ErniePEUnleashed?
Q4_K_M · 2.5 GBErniePEUnleashed (Q4_K_M) requires 2.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. Using the full 262K context window can add up to 20.8 GB, bringing total usage to 23.3 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run ErniePEUnleashed, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 4.3 GB free · up to 64K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~196Simulate output on RTX 3080RTX 2080 Ti~159Simulate output on RTX 2080 TiRTX 3070 Ti~157Simulate output on RTX 3070 TiM3*8 GB~28Simulate output on iMac 24" M3 (8 GB)Orin Nano~26Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~19Simulate output on iPhone 1720 GB
fits · 16.3 GB free · up to 128K ctx
1 GPU
RX 7900 XT~191Simulate output on RX 7900 XT32–40 GB
fits · 28.3 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~462Simulate output on RTX 5090M5 Max36 GB~128Simulate output on Mac Studio M5 Max (36 GB)M532 GB~43Simulate output on MacBook Air 13" M5 (32 GB)Orin~53Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~35Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to ErniePEUnleashed
ERNIE family · 6 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Granite 4.0 MicroIBM | — | 3.7 GB | ~261 | same size |
| Deepseek Vl2 TinyDeepSeek | — | 9.4 GB | ~152 | same size |
| Llama 3.2 3B InstructMeta | — | 4.1 GB | ~309 | same size |
| AI21 Jamba Reasoning 3BAI21 Labs | — | 2.3 GB | ~291 | same size |
| Sarashina2.2 3B Instruct v0.1sbintuitions | — | 3.7 GB | ~247 | same size |
| PowerMoE 3Bibm-research | — | 2.6 GB | ~354 | same size |
Specifications
- Publisher
- Kezmark
- Family
- ERNIE
- Parameters
- 3.4B
- Architecture
- Ministral3ForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2026-05-21
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does ErniePEUnleashed need?
ErniePEUnleashed requires 2.5 GB of VRAM at Q4_K_M, or 7.3 GB at BF16. Full 262K context adds up to 20.8 GB (23.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 3.4B × 4.8 bits ÷ 8 = 2.1 GB
KV Cache + Overhead ≈ 0.4 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 ≈ 21.2 GB (at full 262K context)
VRAM usage by quantization
What's the best quantization for ErniePEUnleashed?
For ErniePEUnleashed, Q4_K_M (2.5 GB) offers the best balance of quality and VRAM usage. Q5_K_M (2.9 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.9 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run ErniePEUnleashed on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run ErniePEUnleashed. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 2.5 GB of usable unified memory (RAM minus macOS overhead).
Can I run ErniePEUnleashed locally?
Yes — ErniePEUnleashed can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is ErniePEUnleashed?
At Q4_K_M, ErniePEUnleashed can reach ~1905 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~260 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 ÷ 2.5200 × 0.65 = ~2063 tok/s
Estimated speed at Q4_K_M (2.5 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of ErniePEUnleashed?
At Q4_K_M, the download is about 2.06 GB. The full-precision BF16 version is 6.86 GB. The smallest option (Q2_K) is 1.46 GB.
Which GPUs can run ErniePEUnleashed?
52 consumer GPUs can run ErniePEUnleashed 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 ErniePEUnleashed?
163 devices with unified memory can run ErniePEUnleashed at Q4_K_M (2.5 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.