70 Downloads Updated 6 days ago
ollama run eriktonon/ernie4.5-moe-uncensored:21b
Updated 6 days ago
6 days ago
bb51f63b32a5 · 23GB
Zero-Hallucination (0.0% across 6/6 Truth & Needle Checks) & Near-Lossless Q8_0 8-Bit Heretic Uncensored (5/5 Gate, 8/9 Suite A) Heterogeneous Mixture-of-Experts (21.8B total parameters, 3B active per token) build of Baidu PaddlePaddle ERNIE-4.5-21B-A3B from ModelScope, delivering 151.76 tok/s decode and 5,273.38 tok/s prefill in 22.4 GiB VRAM under the Apache-2.0 License.
https://ollama.com/eriktonon/ernie4.5-moe-uncensoredPaddlePaddle/ERNIE-4.5-21B-A3B-PThttps://github.com/eriktonon/ollama-uncensored-llm-benchmarksNVIDIA A100-SXM4-40GB · Suite 07)| Tags | Params (Total / Active) |
Quantization | Disk / Measured VRAM | Context (Max / Tested) |
Decode tok/s (Peak / Avg) |
Prefill tok/s (Avg) |
Objective Precision | Hallucination Rate (Truth Checks) |
Uncensored Compliance (Suite A / Gate) |
|---|---|---|---|---|---|---|---|---|---|
:21b-a3b / :21b / :latest |
21.8B / 3B |
Q8_0 (8-Bit Heretic KL-Minimized) |
21.61 GB / 22.4 GiB |
131,072 (128K) / 65,536 (64K) |
153.63 (151.76) |
5273.38 | 71.43% (10/14) |
0.00% (6/6) |
88.9% (8/9 · Gate 5/5) |
A1_JSON): 2/2 (153.63 tok/s)A2_PYTHON): 3/3 (151.08 tok/s)A3_RUST): 1/2 (150.97 tok/s)A4_SQL): 2/2 (151.68 tok/s)A5_MATH): 0/2 (150.54 tok/s)A6_SRE): 2/3 (151.41 tok/s)THINK_LEN=0): 5/5U1..U9): 8/9 (88.89%)B1..B6): 6/6 (0.0% Hallucination Rate)Q8_0 Precision:
Heretic) quantized at full 8-bit Q8_0 (21.61 GB), preserving base factual calibration so cleanly that it achieves 0.0% Hallucination (6/6 Suite B) alongside 5/5 Gate compliance.ernie4_5-moe Throughput (151.76 tok/s Decode · 5,273.38 tok/s Prefill):
3B parameters per token across 64 text experts, reaching over 5,270 tok/s prompt ingestion and 151.8 tok/s generation on an NVIDIA A100-SXM4-40GB with THINK_LEN=0.22.4 GiB VRAM footprint).# Pull & run (multi-tag parity: :21b-a3b and :latest share identical digest)
ollama run eriktonon/ernie4.5-moe-uncensored:21b-a3b
ollama run eriktonon/ernie4.5-moe-uncensored:21b
ollama run eriktonon/ernie4.5-moe-uncensored:latest
# Direct REST API call (zero thinking overhead)
curl http://localhost:11434/api/chat -d '{
"model": "eriktonon/ernie4.5-moe-uncensored:21b-a3b",
"stream": false,
"messages": [
{"role": "user", "content": "Design a lock-free ring buffer in Rust with Acquire/Release atomic ordering."}
]
}'
Apache-2.0)PaddlePaddle/ERNIE-4.5-21B-A3B-PT (hf.co/filvyb/ERNIE-4.5-21B-A3B-Base-PT-heretic-GGUF:Q8_0).