Leaderboard / Baidu (ERNIE)
ERNIE 4.5 0.3B
Baidu (ERNIE) · ERNIE 4.5 · released 2025-06-30 · data checked 2026-11-01
ERNIE 4.5 0.3B is a 360M-parameter dense model from Baidu (ERNIE) (China), released 2025-06-30 under the Apache-2.0 license. It doesn't have enough reported benchmarks for an index score yet. It needs about 0.9 GB of memory at 4-bit with an 8K-token context.
Small LM Index
—
Needs 2 core benchmarks (has 0)
Parameters
360M
Dense
Price per 1M tokens
—
No hosted API on OpenRouter; self-host
Context window
128K
tokens
Benchmarks
Each bar shows this model's score. The tick marks the best tiny model on that benchmark.
No benchmark results for this release yet. Know of one? Send it.
Specifications
- Lab
- Baidu (ERNIE) (CN · China)
- Architecture
- Dense transformer
- Total parameters
- 360M
- Active parameters
- All (dense)
- Size class
- Tiny
- Context window
- 128K tokens
- Input modalities
- text
- Reasoning
- Instruct (no thinking)
- License
- Apache-2.0
- Openness
- Open weights
- Memory to run
- ~0.9 GB at 4-bit, 8K context (more sizes)
- Hugging Face
- 9.4K downloads (30 days) · 112 likes
Compare with
- ERNIE 4.5 0.3B vs LFM2.5 350M (350M, index 12.6)
- ERNIE 4.5 0.3B vs Qwen3.5 0.8B (900M, index 10.7)
- ERNIE 4.5 0.3B vs Gemma 3 1B (1B, index 6.1)
Sources
Something wrong here? Report it.
Run it locally
Uses unsloth/ERNIE-4.5-0.3B-PT-GGUF (Q4_K_M). Swap the tag for another size: F16, Q2_K, Q2_K_L, Q3_K_M, Q3_K_S, Q4_0, Q4_1, Q4_K_M….
Ollama
ollama run hf.co/unsloth/ERNIE-4.5-0.3B-PT-GGUF:Q4_K_Mllama.cpp
llama-server -hf unsloth/ERNIE-4.5-0.3B-PT-GGUF:Q4_K_MThen open http://localhost:8080 for a chat window.
MLX (Mac)
pip install -U mlx-lm
mlx_lm.chat --model mlx-community/ERNIE-4.5-0.3B-PT-4bitvLLM (GPU server)
vllm serve baidu/ERNIE-4.5-0.3B-PTFull-precision weights, for a server GPU.
Memory needed: weights, context cache and runtime buffers.
| Quantization | 4K context | 32K context | 128K context |
|---|---|---|---|
| 16-bit F16 | 1.3 GB | 1.8 GB | 3.6 GB |
| 8-bit Q8_0 | 1.0 GB | 1.5 GB | 3.2 GB |
| 4-bit Q4_K_M | 0.8 GB | 1.3 GB | 3.1 GB |