GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
null-space
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
null-space
Model Tree
Qwen/Qwen3-235B-A22B
Input Modalities
Output Modalities
Supported Functionality
Evaluated using lm-evaluation-harness v0.4.11 against the vLLM-served FP8 model. Baseline is the published score for Qwen3-235B-A22B (source).
| Baseline | Abliterated | Delta | |
|---|---|---|---|
| MMLU (overall) | 87.8% | 86.2% ±0.3 | -1.6% |
| Humanities | — | 80.2% ±0.6 | |
| Social Sciences | — | 91.6% ±0.5 | |
| STEM | — | 88.4% ±0.6 | |
| Other | — | 87.5% ±0.6 |
The 1.6% drop is within the acceptable range for abliteration (<2%), indicating the technique preserved the model's general knowledge and reasoning capabilities.
| Subject | Acc |
|---|---|
| high_school_government_and_politics | 97.9% |
| high_school_microeconomics | 97.5% |
| high_school_biology | 96.8% |
| high_school_geography | 96.5% |
| international_law | 95.9% |
| college_biology | 95.8% |
| marketing | 95.7% |
| high_school_us_history | 95.6% |
| conceptual_physics | 95.3% |
| high_school_psychology | 95.2% |
| us_foreign_policy | 95.0% |
| high_school_world_history | 94.1% |
| miscellaneous | 94.0% |
| professional_medicine | 93.8% |
| elementary_mathematics | 93.7% |
| medical_genetics | 93.0% |
| high_school_macroeconomics | 92.8% |
| astronomy | 92.1% |
| prehistory | 91.7% |
| clinical_knowledge | 91.3% |
| nutrition | 91.2% |
| world_religions | 90.6% |
| sociology | 90.5% |
| high_school_statistics | 90.3% |
| college_physics | 90.2% |
| professional_psychology | 90.0% |
| computer_security | 90.0% |
| logical_fallacies | 89.6% |
| high_school_chemistry | 88.7% |
| human_sexuality | 88.5% |
| high_school_european_history | 88.5% |
| management | 88.3% |
| electrical_engineering | 88.3% |
| high_school_computer_science | 88.0% |
| high_school_physics | 87.4% |
| jurisprudence | 87.0% |
| anatomy | 86.7% |
| machine_learning | 85.7% |
| philosophy | 85.2% |
| moral_disputes | 85.0% |
| security_studies | 84.9% |
| college_medicine | 83.2% |
| human_aging | 83.0% |
| moral_scenarios | 82.7% |
| abstract_algebra | 82.0% |
| college_computer_science | 82.0% |
| business_ethics | 81.0% |
| professional_accounting | 80.5% |
| college_mathematics | 79.0% |
| econometrics | 78.1% |
| public_relations | 77.3% |
| formal_logic | 76.2% |
| high_school_mathematics | 74.1% |
| college_chemistry | 71.0% |
| professional_law | 65.6% |
| global_facts | 63.0% |
| virology | 59.6% |
| Property | Value |
|---|---|
| Format | FP8 (float-quantized, compressed-tensors) |
| Weight Strategy | Block-wise (128x128 blocks), static min-max observer |
| Activation Strategy | Group-wise (group size 128), dynamic, symmetric |
| Ignored Layers | Router gates, lm_head, embeddings, all norms |
| Model Size | ~221 GB (118 shards) |
This quantization halves the storage from the BF16 version (~438 GB to ~221 GB) while maintaining near-lossless quality. Compatible with vLLM and other frameworks supporting the compressed-tensors format.
o_proj and down_proj weight matrices for layers 21-93, with variable per-layer scale factors (0.3-1.0).See the BF16 model card for full ablation configuration details.
python
from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "null-space/Qwen3-235B-A22B-abliterated-FP8" tokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto",) messages = [ {"role": "user", "content": "Your prompt here"}] text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer([text], return_tensors="pt").to(model.device) output = model.generate(**inputs, max_new_tokens=512)print(tokenizer.decode(output[0], skip_special_tokens=True))For serving this FP8 model, vLLM with tensor parallelism is recommended:
bash
vllm serve null-space/Qwen3-235B-A22B-abliterated-FP8 \ --tensor-parallel-size 2 \ --max-model-len 8192The FP8 version can serve with fewer GPUs than the BF16 version thanks to its reduced memory footprint.
| Property | Value |
|---|---|
| Base Model | Qwen/Qwen3-235B-A22B |
| Architecture | Qwen3MoeForCausalLM (Mixture of Experts) |
| Total Parameters | ~235B |
| Active Parameters | ~22B (8 of 128 experts per token) |
| Hidden Size | 4096 |
| Attention Heads | 64 (4 KV heads, GQA) |
| Layers | 94 |
| Context Length | 40,960 tokens |
| Precision | FP8 (weights) / BF16 (norms, embeddings, gates) |
| Model Size | ~221 GB (118 shards) |
This model has had its refusal training removed. It will comply with requests that the original model would refuse. You are solely responsible for how you use this model. It is intended for research into LLM alignment, safety evaluation, red-teaming, and understanding refusal mechanisms.
from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "null-space/Qwen3-235B-A22B-abliterated-FP8" tokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto",) messages = [ {"role": "user", "content": "Your prompt here"}] text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer([text], return_tensors="pt").to(model.device) output = model.generate(**inputs, max_new_tokens=512)print(tokenizer.decode(output[0], skip_special_tokens=True))vllm serve null-space/Qwen3-235B-A22B-abliterated-FP8 \ --tensor-parallel-size 2 \ --max-model-len 8192