GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
AxiangQAQ
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
AxiangQAQ
Model Tree
deepreinforce-ai/Ornith-1.0-35B
Input Modalities
Output Modalities
Supported Functionality
This is an FP8_BLOCK quantized version of llmfan46/Ornith-1.0-35B-uncensored-heretic with an MTP head grafted from Qwen3.6-35B-A3B for speculative decoding.
The uncensored heretic version achieves 90% fewer refusals (9/100 vs 89/100 original) with only 0.0019 KL divergence.
bash
pip install vllm vllm serve AxiangQAQ/Ornith-1.0-35B-uncensored-heretic-FP8-BLOCK \ --served-model-name ornith-35b-uncensored-fp8 \ --quantization compressed-tensors \ --max-model-len 32768 \ --gpu-memory-utilization 0.93 \ --enable-prefix-caching \ --enable-auto-tool-choice \ --tool-call-parser qwen3_xml \ --reasoning-parser qwen3 \ --speculative-config '{"method":"mtp","num_speculative_tokens":3}'Performance-optimized configuration (validated on RTX 4090 48GB):
bash
vllm serve AxiangQAQ/Ornith-1.0-35B-uncensored-heretic-FP8-BLOCK \ --served-model-name ornith-35b-uncensored-fp8 \ --host 0.0.0.0 \ --port 8000 \ --tensor-parallel-size 1 \ --max-model-len 204800 \ --max-num-seqs 8 \ --max-num-batched-tokens 8192 \ --gpu-memory-utilization 0.93 \ --dtype bfloat16 \ --quantization compressed-tensors \ --kv-cache-dtype fp8_e4m3 \ --mm-encoder-tp-mode data \ --mm-processor-cache-type shm \ --mm-shm-cache-max-object-size-mb 512 \ --media-io-kwargs '{"video": {"num_frames": -1}}' \ --attention-backend flashinfer \ --enable-prefix-caching \ --enable-chunked-prefill \ --generation-config vllm \ --max-cudagraph-capture-size 16 \ --speculative-config '{"method":"mtp","num_speculative_tokens":3}' \ --compilation_config.mode VLLM_COMPILE \ --compilation_config.cudagraph_mode PIECEWISE \ --reasoning-parser qwen3 \ --tool-call-parser qwen3_xml \ --enable-auto-tool-choice \ --trust-remote-codeGPU Requirements: ~40GB VRAM minimum (model is ~38GB FP8). The configuration above was validated on a modified RTX 4090 48GB. For lower VRAM GPUs, quantization to GGUF format is recommended instead.
bash
pip install sglang python3 -m sglang.launch_server \ --model-path AxiangQAQ/Ornith-1.0-35B-uncensored-heretic-FP8-BLOCK \ --host 0.0.0.0 \ --port 30000python
from transformers import AutoModelForMultimodalLM, AutoProcessor model = AutoModelForMultimodalLM.from_pretrained( "AxiangQAQ/Ornith-1.0-35B-uncensored-heretic-FP8-BLOCK", torch_dtype="auto", device_map="auto", trust_remote_code=True,)processor = AutoProcessor.from_pretrained( "AxiangQAQ/Ornith-1.0-35B-uncensored-heretic-FP8-BLOCK", trust_remote_code=True,)Note: This model has not been benchmarked. The data below is from the reference model shisa-ai/Ornith-1.0-35B-FP8-BLOCK-MTP and is provided for reference only.
Reference benchmarks (RTX PRO 6000 Blackwell, single GPU):
| Config | Output tok/s | vs Baseline | TTFT (ms) | TPOT (ms) | Acceptance |
|---|---|---|---|---|---|
| No speculative | 203.1 | — | 51.7 | 4.65 | — |
| MTP tokens=1 | 221.0 | +8.8% | 60.3 | 4.21 | 85.8% |
| MTP tokens=3 | 246.5 |
compressed-tensors format)Ignored layers: lm_head, embed_tokens, visual.*, mlp.gate, mlp.shared_expert_gate, linear_attn.*, mtp.*
text
deepreinforce-ai/Ornith-1.0-35B (MIT, original) └── llmfan46/Ornith-1.0-35B-uncensored-heretic (Heretic v1.2.0 MPOA ablation) └── AxiangQAQ/Ornith-1.0-35B-uncensored-heretic-FP8-BLOCK (this model) ├── FP8_BLOCK quantization (llmcompressor) └── MTP head grafted from Qwen/Qwen3.6-35B-A3B (donor only)| Component | Source |
|---|---|
| Original Model | deepreinforce-ai/Ornith-1.0-35B |
| Uncensored Version | llmfan46/Ornith-1.0-35B-uncensored-heretic |
| FP8 Quantization Reference | shisa-ai/Ornith-1.0-35B-FP8-BLOCK |
| MTP Graft Technique | protoLabsAI/Ornith-1.0-9B-MTP |
| MTP Donor |
MIT — same as the source Ornith-1.0-35B model.
bibtex
@misc{ornith-35b, title = {{Ornith-1.0-35B}: Agentic Coding, Open to All}, url = {https://deep-reinforce.com/ornith_1_0.html}, author = {{DeepReinforce Team}}, year = {2026}}| +21.4% |
| 65.5 |
| 3.57 |
| 67.0% |
| Chat Template Fix | froggeric/Qwen-Fixed-Chat-Templates |
deepreinforce-ai/Ornith-1.0-35B (MIT, original) └── llmfan46/Ornith-1.0-35B-uncensored-heretic (Heretic v1.2.0 MPOA ablation) └── AxiangQAQ/Ornith-1.0-35B-uncensored-heretic-FP8-BLOCK (this model) ├── FP8_BLOCK quantization (llmcompressor) └── MTP head grafted from Qwen/Qwen3.6-35B-A3B (donor only)pip install vllm vllm serve AxiangQAQ/Ornith-1.0-35B-uncensored-heretic-FP8-BLOCK \ --served-model-name ornith-35b-uncensored-fp8 \ --quantization compressed-tensors \ --max-model-len 32768 \ --gpu-memory-utilization 0.93 \ --enable-prefix-caching \ --enable-auto-tool-choice \ --tool-call-parser qwen3_xml \ --reasoning-parser qwen3 \ --speculative-config '{"method":"mtp","num_speculative_tokens":3}'vllm serve AxiangQAQ/Ornith-1.0-35B-uncensored-heretic-FP8-BLOCK \ --served-model-name ornith-35b-uncensored-fp8 \ --host 0.0.0.0 \ --port 8000 \ --tensor-parallel-size 1 \ --max-model-len 204800 \ --max-num-seqs 8 \ --max-num-batched-tokens 8192 \ --gpu-memory-utilization 0.93 \ --dtype bfloat16 \ --quantization compressed-tensors \ --kv-cache-dtype fp8_e4m3 \ --mm-encoder-tp-mode data \ --mm-processor-cache-type shm \ --mm-shm-cache-max-object-size-mb 512 \ --media-io-kwargs '{"video": {"num_frames": -1}}' \ --attention-backend flashinfer \ --enable-prefix-caching \ --enable-chunked-prefill \ --generation-config vllm \ --max-cudagraph-capture-size 16 \ --speculative-config '{"method":"mtp","num_speculative_tokens":3}' \ --compilation_config.mode VLLM_COMPILE \ --compilation_config.cudagraph_mode PIECEWISE \ --reasoning-parser qwen3 \ --tool-call-parser qwen3_xml \ --enable-auto-tool-choice \ --trust-remote-codepip install sglang python3 -m sglang.launch_server \ --model-path AxiangQAQ/Ornith-1.0-35B-uncensored-heretic-FP8-BLOCK \ --host 0.0.0.0 \ --port 30000from transformers import AutoModelForMultimodalLM, AutoProcessor model = AutoModelForMultimodalLM.from_pretrained( "AxiangQAQ/Ornith-1.0-35B-uncensored-heretic-FP8-BLOCK", torch_dtype="auto", device_map="auto", trust_remote_code=True,)processor = AutoProcessor.from_pretrained( "AxiangQAQ/Ornith-1.0-35B-uncensored-heretic-FP8-BLOCK", trust_remote_code=True,)@misc{ornith-35b, title = {{Ornith-1.0-35B}: Agentic Coding, Open to All}, url = {https://deep-reinforce.com/ornith_1_0.html}, author = {{DeepReinforce Team}}, year = {2026}}