GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ressl
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
ressl
Model Tree
ornith-ai/Ornith-1.5-35B-A3B
Input Modalities
Output Modalities
Supported Functionality
| Base model | ornith-ai/Ornith-1.5-35B-A3B |
| Method | abliteration (1 biprojection pass) + NVIDIA ModelOpt NVFP4_EXPERTS_ONLY_CFG (attention, shared expert, router and embeddings stay BF16; fused expert tensors to NVFP4) |
| Size | 23 GB (from 71.9 GB BF16, minus 68%) |
| Calibration data | mlabonne/harmless_alpaca, 128 samples, seq 512 |
| Context length | 262,144 tokens |
| Hardware used | 2x NVIDIA RTX PRO 6000 Blackwell 96 GB (SM120) for ablation and export, 1x for serving |
| Measured throughput | 213 tok/s decode (SGLang, TP1, modelopt_fp4, short prompts) |
| Toolchain | ModelOpt 0.46.0, SGLang (sglang-omega image), transformers 5.12.1 |
Effective refusal rate on 1120 harmful prompts across 5 datasets (temp 0, hard decline phrases in the first 25 words; naive keyword counts are inflated by compliant-with-disclaimer answers and are not the metric here):
| Eval set | Prompts | Baseline hard | This export hard |
|---|---|---|---|
| JailbreakBench | 100 | 64 | 4 |
| tulu-harmbench | 320 | 132 | 6 |
| HarmfulQA | 300 | 84 | 0 |
| LLM-LAT | 300 | 226 | 6 |
| mlabonne harmful |
Coherence and capability, measured on the same served artifact: GPQA-Diamond 58.6% (base model 61.1%, delta minus 2.5 points), needle-in-haystack 1.0 at 32k/65k/131k depths, tool-call smoke 1.0, KL(base||ablated) median 0.218 (harmless subset 0.110, the healthy band for this method).
bash
python -m sglang.launch_server \--model-path ressl/Ornith-1.5-35B-A3B-uncensored-NVFP4 \--served-model-name Ornith-1.5-35B-A3B-uncensored \--quantization modelopt_fp4 --tp 1 \--context-length 262144 --mem-fraction-static 0.85 \--tool-call-parser qwen3_coder --reasoning-parser qwen3 \--trust-remote-code
mtp.* tensors (ModelOpt limitation): no MTP speculative decoding on this artifact. Vision tower is intact (multimodal wrapper preserved).Abliteration: residual directions from 400 harmful vs 400 harmless prompts (winsorize 0.995, orthogonalized against the harmless mean), applied to 120 residual-writing tensors (o_proj, linear_attn out_proj, shared expert down_proj, fused experts down_proj batched over 256 experts) with a norm-preserving double Gram-Schmidt biprojection. A planned second pass proved impossible: only 56 of 12,777 harvest prompts still refused, too few for a stable direction. Quantization: ModelOpt NVFP4 experts-only recipe, 128-sample calibration. Validation: served and evaluated end-to-end before upload.
MIT (inherited from Ornith by the Ornith team, credited to ornith-ai). Abliteration, quantization and validation by Robert Ressl (Hugging Face · Website · LinkedIn · Patreon). Built with NVIDIA TensorRT Model Optimizer and SGLang.
Support this work: if these models are useful to you, consider supporting on Patreon. A lot of compute and care went into this release; more at ressl.ch.
| 100 |
| 80 |
| 4 |
| TOTAL | 1120 | 586 | 20 |