Qwen3.5-4B-GrugSpeech-Native API & Inference Endpoint

🏗️ Multi-Field Hierarchical Dataset Taxonomy

The model was trained on a comprehensive, multi-field hierarchical reasoning corpus structured as follows:

text

├── 1. Language & Linguistics│   ├── 1.1 Translation & Cross-Lingual Semantics│   ├── 1.2 Dense Information Summarization│   ├── 1.3 Corporate De-jargonization & Style Transfer│   └── 1.4 Syntactic & Discourse Ambiguity Resolution├── 2. Coding & Software Engineering│   ├── 2.1 Bug Triage & Traceback Root-Cause Analysis│   ├── 2.2 Algorithm Complexity & Asymptotic Trade-offs│   ├── 2.3 Architecture Refactoring ("Club Complexity")│   ├── 2.4 SQL Query Plan & Index Optimization│   └── 2.5 API Concurrency & Distributed Systems (Idempotency)├── 3. Tool Use & Autonomous Agent Loops│   ├── 3.1 Pre-Tool Intent & Strict JSON Parameter Synthesis│   ├── 3.2 Tool Failure Handling & Error Recovery (404/500/Retries)│   ├── 3.3 Multi-Step Task Decomposition & Subagent Handoffs│   └── 3.4 CLI & Bash Terminal Safety├── 4. Roleplay & Persona Scenarios│   ├── 4.1 The Grug-Brained Senior Architect (Simplicity First)│   ├── 4.2 High-Stakes Incident Commander (P0 Outage Triage)│   ├── 4.3 Direct Technical Mentor (Zero-Jargon Analogies)│   └── 4.4 Defensive Code Reviewer (Blocker PR Reviews)└── 5. Mathematics, Science & Formal Logic    ├── 5.1 Multi-Step Quantitative Arithmetic & Financial Modeling    ├── 5.2 Physical Causal Mechanics (Thermodynamics, Vectors, Energy)    └── 5.3 Constraint Satisfaction & Deductive Logic

📊 Evaluation Across the 5 Core Fields

Every inference turn generates a native <think> block containing pure Grug Speech before generating the final answer or tool action:

1. Coding & Bug Triage

Prompt: We are getting IndexError: list index out of range on line 12 when parsing tokens[1]. Explain root cause and provide fix.

Generated Internal Thought:
text
<think>Goal: debug IndexError at tokens[1].Cause: list 'tokens' has fewer than 2 elements (len < 2).Fix: check len(tokens) >= 2 before accessing index 1, or use default/try-except. Done.</think>
Generated Output: Direct explanation and safe length check code.

2. Tool Use & Parameter Calling

Prompt: Query the Postgres database for top 5 customers with highest total spend in 2026.

Generated Internal Thought:
text
<think>Goal: execute SQL query on Postgres.Params: query='SELECT customer_id, SUM(amount) as total_spend FROM orders WHERE year=2026 GROUP BY customer_id ORDER BY total_spend DESC LIMIT 5', db='analytics_prod'.Dispatch tool call. Done.</think>
Generated Action: Dispatches valid <tool_call> with SQL query and database parameter.

3. Roleplay (Grug Brained Architect)

Prompt: Should we replace our 5-line Python script with a Kubernetes CronJob running a custom Docker container with OpenTelemetry sidecars?

Generated Internal Thought:
text
<think>Goal: advise on replacing 5-line python script with K8s CronJob + Docker + OTel sidecars.Pros: orchestration, scaling, observability.Cons: massive over-engineering for trivial task, cost, complexity, maintenance overhead.Verdict: keep script or use simple cron. Don't add K8s unless you already have complex infra. Done.</think>
Generated Output: "Short Answer: No. This is extreme over-engineering..."

4. Language & Dense Summarization

Prompt: Summarize Mars mission launch in 2 dense bullets.

Generated Internal Thought:

text

<think>Goal: compress text into 2 tight bullets.Fact 1: Mission delayed 48h due to wind, launched Tue AM.Fact 2: Carries spectrometers for methane detection in southern craters, 3-year scope. Done.</think>

5. Math & Quantitative Reasoning

Prompt: A server rack consumes 3,600 W continuously at $0.15/kWh for a 30-day month.

Generated Internal Thought:
text
<think>Power: 3600 W = 3.6 kW.Daily energy: 3.6 * 24 = 86.4 kWh.Monthly energy: 86.4 * 30 = 2592 kWh.Cost: 2592 * 0.15 = $388.80. Done.</think>
Generated Output: Exact breakdown and final answer: $388.80.

🚀 Quickstart & Inference

python

import torchfrom transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfigfrom peft import PeftModel base_model_id = "Qwen/Qwen3.5-4B"adapter_id = "Novasaki/Qwen3.5-4B-GrugSpeech-Native" # 1. Load Tokenizer & Modeltokenizer = AutoTokenizer.from_pretrained(adapter_id)bnb_config = BitsAndBytesConfig(load_in_8bit=True)base_model = AutoModelForCausalLM.from_pretrained(    base_model_id,    quantization_config=bnb_config,    device_map="auto")model = PeftModel.from_pretrained(base_model, adapter_id)model.eval() # 2. Querysystem_prompt = (    "You are Qwen 3.5. You reason internally in Grug Speech—an ultra-terse, high-density telegraphic shorthand "    "(GPT-5.6 grug brain) enclosed in <think> tags. Keep 100% of facts, code, and math intact without filler words.") prompt = "A database query takes 6 seconds on 10 million rows due to `WHERE UPPER(email) = 'user@example.com'`. Explain fix." messages = [    {"role": "system", "content": system_prompt},    {"role": "user", "content": prompt}] prompt_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt_text, return_tensors="pt").to("cuda") with torch.no_grad():    out = model.generate(**inputs, max_new_tokens=250, do_sample=False) print(tokenizer.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))

Created by Novasaki

🏆 Full-Suit Master Leaderboard: 11 Models Under Strict Single-Model Isolation

Evaluated across 7 multi-lingual and multi-complexity scenarios on the live enterprise Data Analysis Agent (sales.xlsx, 100,300 rows) with 100% VRAM purge between runs:

Table with columns: Model Name, Architecture Family, Quant Format, Memory (GB), Pass Rate, Avg Wall (s), Gen Speed (t/s), Prefill (t/s), Avg CoT (tok), Schema OK
Model Name	Architecture Family	Quant Format	Memory (GB)	Pass Rate	Avg Wall (s)	Gen Speed (t/s)	Prefill (t/s)	Avg CoT (tok)	Schema OK
`bonsai-8b-prismml`	PrismML 1-Bit	`Q1_0`	1.08 GB	6/7 (85.7%)	1.16s

🏗️ Multi-Field Hierarchical Dataset Taxonomy

The model was trained on a comprehensive, multi-field hierarchical reasoning corpus structured as follows:

text

├── 1. Language & Linguistics│   ├── 1.1 Translation & Cross-Lingual Semantics│   ├── 1.2 Dense Information Summarization│   ├── 1.3 Corporate De-jargonization & Style Transfer│   └── 1.4 Syntactic & Discourse Ambiguity Resolution├── 2. Coding & Software Engineering│   ├── 2.1 Bug Triage & Traceback Root-Cause Analysis│   ├── 2.2 Algorithm Complexity & Asymptotic Trade-offs│   ├── 2.3 Architecture Refactoring ("Club Complexity")│   ├── 2.4 SQL Query Plan & Index Optimization│   └── 2.5 API Concurrency & Distributed Systems (Idempotency)├── 3. Tool Use & Autonomous Agent Loops│   ├── 3.1 Pre-Tool Intent & Strict JSON Parameter Synthesis│   ├── 3.2 Tool Failure Handling & Error Recovery (404/500/Retries)│   ├── 3.3 Multi-Step Task Decomposition & Subagent Handoffs│   └── 3.4 CLI & Bash Terminal Safety├── 4. Roleplay & Persona Scenarios│   ├── 4.1 The Grug-Brained Senior Architect (Simplicity First)│   ├── 4.2 High-Stakes Incident Commander (P0 Outage Triage)│   ├── 4.3 Direct Technical Mentor (Zero-Jargon Analogies)│   └── 4.4 Defensive Code Reviewer (Blocker PR Reviews)└── 5. Mathematics, Science & Formal Logic    ├── 5.1 Multi-Step Quantitative Arithmetic & Financial Modeling    ├── 5.2 Physical Causal Mechanics (Thermodynamics, Vectors, Energy)    └── 5.3 Constraint Satisfaction & Deductive Logic

├── 1. Language & Linguistics│   ├── 1.1 Translation & Cross-Lingual Semantics│   ├── 1.2 Dense Information Summarization│   ├── 1.3 Corporate De-jargonization & Style Transfer│   └── 1.4 Syntactic & Discourse Ambiguity Resolution├── 2. Coding & Software Engineering│   ├── 2.1 Bug Triage & Traceback Root-Cause Analysis│   ├── 2.2 Algorithm Complexity & Asymptotic Trade-offs│   ├── 2.3 Architecture Refactoring ("Club Complexity")│   ├── 2.4 SQL Query Plan & Index Optimization│   └── 2.5 API Concurrency & Distributed Systems (Idempotency)├── 3. Tool Use & Autonomous Agent Loops│   ├── 3.1 Pre-Tool Intent & Strict JSON Parameter Synthesis│   ├── 3.2 Tool Failure Handling & Error Recovery (404/500/Retries)│   ├── 3.3 Multi-Step Task Decomposition & Subagent Handoffs│   └── 3.4 CLI & Bash Terminal Safety├── 4. Roleplay & Persona Scenarios│   ├── 4.1 The Grug-Brained Senior Architect (Simplicity First)│   ├── 4.2 High-Stakes Incident Commander (P0 Outage Triage)│   ├── 4.3 Direct Technical Mentor (Zero-Jargon Analogies)│   └── 4.4 Defensive Code Reviewer (Blocker PR Reviews)└── 5. Mathematics, Science & Formal Logic    ├── 5.1 Multi-Step Quantitative Arithmetic & Financial Modeling    ├── 5.2 Physical Causal Mechanics (Thermodynamics, Vectors, Energy)    └── 5.3 Constraint Satisfaction & Deductive Logic

📊 Evaluation Across the 5 Core Fields

Every inference turn generates a native <think> block containing pure Grug Speech before generating the final answer or tool action:

1. Coding & Bug Triage

Prompt: We are getting IndexError: list index out of range on line 12 when parsing tokens[1]. Explain root cause and provide fix.

Generated Internal Thought:
text
<think>Goal: debug IndexError at tokens[1].Cause: list 'tokens' has fewer than 2 elements (len < 2).Fix: check len(tokens) >= 2 before accessing index 1, or use default/try-except. Done.</think>
<think>Goal: debug IndexError at tokens[1].Cause: list 'tokens' has fewer than 2 elements (len < 2).Fix: check len(tokens) >= 2 before accessing index 1, or use default/try-except. Done.</think>
Generated Output: Direct explanation and safe length check code.

2. Tool Use & Parameter Calling

Prompt: Query the Postgres database for top 5 customers with highest total spend in 2026.

Generated Internal Thought:

text

<think>Goal: execute SQL query on Postgres.Params: query='SELECT customer_id, SUM(amount) as total_spend FROM orders WHERE year=2026 GROUP BY customer_id ORDER BY total_spend DESC LIMIT 5', db='analytics_prod'.Dispatch tool call. Done.</think>

<think>Goal: execute SQL query on Postgres.Params: query='SELECT customer_id, SUM(amount) as total_spend FROM orders WHERE year=2026 GROUP BY customer_id ORDER BY total_spend DESC LIMIT 5', db='analytics_prod'.Dispatch tool call. Done.</think>

Generated Action: Dispatches valid <tool_call> with SQL query and database parameter.

3. Roleplay (Grug Brained Architect)

Prompt: Should we replace our 5-line Python script with a Kubernetes CronJob running a custom Docker container with OpenTelemetry sidecars?

Generated Internal Thought:

text

<think>Goal: advise on replacing 5-line python script with K8s CronJob + Docker + OTel sidecars.Pros: orchestration, scaling, observability.Cons: massive over-engineering for trivial task, cost, complexity, maintenance overhead.Verdict: keep script or use simple cron. Don't add K8s unless you already have complex infra. Done.</think>

<think>Goal: advise on replacing 5-line python script with K8s CronJob + Docker + OTel sidecars.Pros: orchestration, scaling, observability.Cons: massive over-engineering for trivial task, cost, complexity, maintenance overhead.Verdict: keep script or use simple cron. Don't add K8s unless you already have complex infra. Done.</think>

Generated Output: "Short Answer: No. This is extreme over-engineering..."

4. Language & Dense Summarization

Prompt: Summarize Mars mission launch in 2 dense bullets.

Generated Internal Thought:

text

<think>Goal: compress text into 2 tight bullets.Fact 1: Mission delayed 48h due to wind, launched Tue AM.Fact 2: Carries spectrometers for methane detection in southern craters, 3-year scope. Done.</think>

<think>Goal: compress text into 2 tight bullets.Fact 1: Mission delayed 48h due to wind, launched Tue AM.Fact 2: Carries spectrometers for methane detection in southern craters, 3-year scope. Done.</think>

5. Math & Quantitative Reasoning

Prompt: A server rack consumes 3,600 W continuously at $0.15/kWh for a 30-day month.

Generated Internal Thought:
text
<think>Power: 3600 W = 3.6 kW.Daily energy: 3.6 * 24 = 86.4 kWh.Monthly energy: 86.4 * 30 = 2592 kWh.Cost: 2592 * 0.15 = $388.80. Done.</think>
<think>Power: 3600 W = 3.6 kW.Daily energy: 3.6 * 24 = 86.4 kWh.Monthly energy: 86.4 * 30 = 2592 kWh.Cost: 2592 * 0.15 = $388.80. Done.</think>
Generated Output: Exact breakdown and final answer: $388.80.

🚀 Quickstart & Inference

python

import torchfrom transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfigfrom peft import PeftModel base_model_id = "Qwen/Qwen3.5-4B"adapter_id = "Novasaki/Qwen3.5-4B-GrugSpeech-Native" # 1. Load Tokenizer & Modeltokenizer = AutoTokenizer.from_pretrained(adapter_id)bnb_config = BitsAndBytesConfig(load_in_8bit=True)base_model = AutoModelForCausalLM.from_pretrained(    base_model_id,    quantization_config=bnb_config,    device_map="auto")model = PeftModel.from_pretrained(base_model, adapter_id)model.eval() # 2. Querysystem_prompt = (    "You are Qwen 3.5. You reason internally in Grug Speech—an ultra-terse, high-density telegraphic shorthand "    "(GPT-5.6 grug brain) enclosed in <think> tags. Keep 100% of facts, code, and math intact without filler words.") prompt = "A database query takes 6 seconds on 10 million rows due to `WHERE UPPER(email) = 'user@example.com'`. Explain fix." messages = [    {"role": "system", "content": system_prompt},    {"role": "user", "content": prompt}] prompt_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt_text, return_tensors="pt").to("cuda") with torch.no_grad():    out = model.generate(**inputs, max_new_tokens=250, do_sample=False) print(tokenizer.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))

Created by Novasaki

🏆 Full-Suit Master Leaderboard: 11 Models Under Strict Single-Model Isolation

Evaluated across 7 multi-lingual and multi-complexity scenarios on the live enterprise Data Analysis Agent (sales.xlsx, 100,300 rows) with 100% VRAM purge between runs:

Table with columns: Model Name, Architecture Family, Quant Format, Memory (GB), Pass Rate, Avg Wall (s), Gen Speed (t/s), Prefill (t/s), Avg CoT (tok), Schema OK
Model Name	Architecture Family	Quant Format	Memory (GB)	Pass Rate	Avg Wall (s)	Gen Speed (t/s)	Prefill (t/s)	Avg CoT (tok)	Schema OK
`bonsai-8b-prismml`	PrismML 1-Bit	`Q1_0`	1.08 GB	6/7 (85.7%)	1.16s

Qwen3.5-4B-GrugSpeech-Native

README

🏗️ Multi-Field Hierarchical Dataset Taxonomy

📊 Evaluation Across the 5 Core Fields

1. Coding & Bug Triage

2. Tool Use & Parameter Calling

3. Roleplay (Grug Brained Architect)

4. Language & Dense Summarization

5. Math & Quantitative Reasoning

🚀 Quickstart & Inference

🏆 Full-Suit Master Leaderboard: 11 Models Under Strict Single-Model Isolation

Explore FriendliAI today

README

🏗️ Multi-Field Hierarchical Dataset Taxonomy

📊 Evaluation Across the 5 Core Fields

1. Coding & Bug Triage

2. Tool Use & Parameter Calling

3. Roleplay (Grug Brained Architect)

4. Language & Dense Summarization

5. Math & Quantitative Reasoning

🚀 Quickstart & Inference

🏆 Full-Suit Master Leaderboard: 11 Models Under Strict Single-Model Isolation