GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ValiantLabs
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
ValiantLabs
Model Tree
google/gemma-4-12B-it
Input Modalities
Output Modalities
Supported Functionality
Esper 4 uses the gemma-4-12B-it prompt format.
Use Esper 4 with your agentic framework of choice or as a stand-alone chat and code assistant.
Example inference script to get started:
python
from transformers import AutoProcessor, AutoModelForCausalLM MODEL_ID = "ValiantLabs/gemma-4-12B-it-Esper4" # Load modelprocessor = AutoProcessor.from_pretrained(MODEL_ID)model = AutoModelForCausalLM.from_pretrained( MODEL_ID, dtype="auto", device_map="auto") # Prepare the model inputprompt = "Implement CQRS for network appliance config management.\n\nRequirements:\n- Write side: 200 commands/sec, 4 command handlers, SQLite with custom journaling\n- Read side: 1000 queries/sec, 3 read projections in shared memory segments\n- Eventual consistency window: 100ms max\n- Handle atomic swap of projection memory for rebuilds\n- Binary configuration format versioning for schema evolution\n- Framework: libevent with custom protocol parser\n\nConstraints:\n- Manual memory management only, no garbage collection\n- Lock-free data structures where possible\n- Shared memory projections must survive process restarts\n- Command handlers must be thread-safe with 4 worker threads\n- Projection rebuild must not block queries\n- Binary format must support forward/backward compatibility\n- Error handling for corrupted journal recovery\n- Memory-mapped I/O for shared segments\n- Zero-copy where possible for performance\n\nDeliverables:\n1. Command processing pipeline with journaling\n2. Projection engine with shared memory management\n3. Query dispatcher with read-your-writes consistency\n4. Schema evolution system with versioned binary format\n5. Integration with libevent for network I/O\n6. Stress test showing 200 cmd/s + 1000 q/s sustained\n\nAssume x86_64 Linux, pthreads, atomic operations. No high-level frameworks." messages = [ {"role": "user", "content": prompt},] # Process inputtext = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=True)inputs = processor(text=text, return_tensors="pt").to(model.device)input_len = inputs["input_ids"].shape[-1] # Generate outputoutputs = model.generate(**inputs, max_new_tokens=40000)response = processor.decode(outputs[0][input_len:], skip_special_tokens=False) # Parse outputprocessor.parse_response(response)print(response)
Esper 4 is created by Valiant Labs.
Check out our HuggingFace page to see all of our models!
We care about open source. For everyone to use.
from transformers import AutoProcessor, AutoModelForCausalLM MODEL_ID = "ValiantLabs/gemma-4-12B-it-Esper4" # Load modelprocessor = AutoProcessor.from_pretrained(MODEL_ID)model = AutoModelForCausalLM.from_pretrained( MODEL_ID, dtype="auto", device_map="auto") # Prepare the model inputprompt = "Implement CQRS for network appliance config management.\n\nRequirements:\n- Write side: 200 commands/sec, 4 command handlers, SQLite with custom journaling\n- Read side: 1000 queries/sec, 3 read projections in shared memory segments\n- Eventual consistency window: 100ms max\n- Handle atomic swap of projection memory for rebuilds\n- Binary configuration format versioning for schema evolution\n- Framework: libevent with custom protocol parser\n\nConstraints:\n- Manual memory management only, no garbage collection\n- Lock-free data structures where possible\n- Shared memory projections must survive process restarts\n- Command handlers must be thread-safe with 4 worker threads\n- Projection rebuild must not block queries\n- Binary format must support forward/backward compatibility\n- Error handling for corrupted journal recovery\n- Memory-mapped I/O for shared segments\n- Zero-copy where possible for performance\n\nDeliverables:\n1. Command processing pipeline with journaling\n2. Projection engine with shared memory management\n3. Query dispatcher with read-your-writes consistency\n4. Schema evolution system with versioned binary format\n5. Integration with libevent for network I/O\n6. Stress test showing 200 cmd/s + 1000 q/s sustained\n\nAssume x86_64 Linux, pthreads, atomic operations. No high-level frameworks." messages = [ {"role": "user", "content": prompt},] # Process inputtext = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=True)inputs = processor(text=text, return_tensors="pt").to(model.device)input_len = inputs["input_ids"].shape[-1] # Generate outputoutputs = model.generate(**inputs, max_new_tokens=40000)response = processor.decode(outputs[0][input_len:], skip_special_tokens=False) # Parse outputprocessor.parse_response(response)print(response)