GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
RedHatAI
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
RedHatAI
Model Tree
Qwen/Qwen3.6-35B-A3B
Input Modalities
Output Modalities
Supported Functionality
This model was evaluated on GSM8K-Platinum, MMLU-Pro, IFEval, Math 500, GPQA Diamond, AIME 25, and LiveCodeBench v6 using lm-evaluation-harness and lighteval, served with vLLM using --language-model-only.
| Benchmark | Qwen/Qwen3.6-35B-A3B | RedHatAI/Qwen3.6-35B-A3B-NVFP4 | Recovery (%) |
|---|---|---|---|
| GSM8k Platinum (0-shot) | 95.73 | 96.08 | 100.37 |
| IfEval (0-shot) | 93.09 | 92.45 | 99.31 |
| AIME 2025 | 92.92 | 91.25 | 98.21 |
| GPQA diamond | 84.51 | 84.68 | 100.20 |
| Math 500 | 84.80 | 85.00 | 100.24 |
| Lcb Codegeneration V6 | 77.33 | 74.67 | 96.55 |
| MMLU Pro Chat | 85.32 | 84.70 | 99.28 |
| BFCLv4 Overall | 57.83 | 56.10 | 97.01 |
| BFCLv4 Single Turn | 53.81 | 53.45 | 99.34 |
| BFCLv4 Multi-Turn | 62.25 | 58.13 | 93.38 |
| BFCLv4 Agentic | 49.91 | 49.31 | 98.80 |
| SWEBench Verified | 54.8 | 50.2 | 91.61 |
The results were obtained using the following commands:
The model was served with vLLM using the following command:
markdown
vllm serve RedHatAI/Qwen3.6-35B-A3B-NVFP4 --reasoning-parser qwen3 --language-model-only --max-model-len 96000
Each benchmark was run 3 times with different seeds (42, 1234, 4158), except AIME 25 which used 8 seeds (42, 1234, 4158, 5322, 1356, 9843, 3344, 5678). Scores are averaged across all seeds.
markdown
lm_eval --model local-chat-completions \--tasks gsm8k_platinum_cot_llama \--model_args "model=RedHatAI/Qwen3.6-35B-A3B-NVFP4,max_length=96000,base_url=http://0.0.0.0:8000/v1/chat/completions,num_concurrent=128,max_retries=3,tokenized_requests=False,tokenizer_backend=None,timeout=2400" \--num_fewshot 0 \--apply_chat_template \--output_path results.json \--seed 42 \--gen_kwargs "do_sample=true,temperature=1.0,top_p=0.95,top_k=20,min_p=0.0,max_gen_toks=64000,presence_penalty=1.5,repetition_penalty=1.0,seed=42"
markdown
lm_eval --model local-chat-completions \--tasks ifeval \--model_args "model=RedHatAI/Qwen3.6-35B-A3B-NVFP4,max_length=96000,base_url=http://0.0.0.0:8000/v1/chat/completions,num_concurrent=128,max_retries=3,tokenized_requests=False,tokenizer_backend=None,timeout=2400" \--apply_chat_template \--output_path results.json \--seed 42 \--gen_kwargs "do_sample=true,temperature=1.0,top_p=0.95,top_k=20,min_p=0.0,max_gen_toks=64000,presence_penalty=1.5,repetition_penalty=1.0,seed=42"
markdown
lm_eval --model local-chat-completions \--tasks mmlu_pro_chat \--model_args "model=RedHatAI/Qwen3.6-35B-A3B-NVFP4,max_length=96000,base_url=http://0.0.0.0:8000/v1/chat/completions,num_concurrent=128,max_retries=3,tokenized_requests=False,tokenizer_backend=None,timeout=3600" \--num_fewshot 0 \--apply_chat_template \--output_path results.json \--seed 42 \--gen_kwargs "do_sample=true,temperature=1.0,top_p=0.95,top_k=20,min_p=0.0,max_gen_toks=64000,presence_penalty=1.5,repetition_penalty=1.0,seed=42"
litellm_config.yaml:
yaml
model_parameters:provider: "hosted_vllm"model_name: "hosted_vllm/RedHatAI/Qwen3.6-35B-A3B-NVFP4"base_url: "http://0.0.0.0:8000/v1"api_key: ""timeout: 2400concurrent_requests: 64generation_parameters:temperature: 1.0max_new_tokens: 64000top_p: 0.95top_k: 20min_p: 0.0presence_penalty: 1.5repetition_penalty: 1.0seed: 0
markdown
lighteval endpoint litellm litellm_config.yaml \"math_500|0,gpqa:diamond|0,lcb:codegeneration_v6|0" \--output-dir results \--save-details
markdown
lighteval endpoint litellm litellm_config.yaml \"aime25|0" \--output-dir results \--save-details
BFCL requires the model to be registered in the leaderboard codebase before running evaluation.
Step 1 — Register the model in bfcl_eval/constants/model_config.py
Add the following entry to api_inference_model_map:
python
"Qwen3.6-35B-A3B-NVFP4": ModelConfig(model_name="Qwen3.6-35B-A3B-NVFP4",display_name="Qwen3.6-35B-A3B-NVFP4 (FC)",url="https://huggingface.co/RedHatAI/Qwen3.6-35B-A3B-NVFP4",org="Google",license="Apache 2.0",model_handler=OpenAICompletionsHandler,input_price=None,output_price=None,is_fc_model=True,underscore_to_dot=True,),
Step 2 — Add the key to bfcl_eval/constants/supported_models.py
Add "Qwen3.6-35B-A3B-NVFP4" to the SUPPORTED_MODELS list.
Step 3 — Start the vLLM server (use the command at the top of this section; the --served-model-name flag ensures BFCL can find the model by its registered slug).
Step 4 — Generate responses and evaluate
markdown
bfcl generate --model Qwen3.6-35B-A3B-NVFP4 --test-category allbfcl evaluate --model Qwen3.6-35B-A3B-NVFP4 --test-category all