Harmonic-27B-GGUF

GGUF quantizations of DJLougen/Harmonic-27B — the flagship of the Harmonic series. A reasoning-focused fine-tune of Qwen 3.5 27B trained on structurally validated data. Every row passes automated quality gates. No junk, no filler, no shallow traces.

The name comes from harmonic analysis of reasoning patterns — the structural signal that separates genuine thinking from surface-level chain-of-thought.

Available Quantizations

File	Quant	Size	Description
Harmonic-27B-F16.gguf	F16	51 GB	Full precision — no quality loss
Harmonic-27B-Q8_0.gguf	Q8_0	27 GB	8-bit — near-lossless quality
Harmonic-27B-Q4_K_M.gguf	Q4_K_M	16 GB	4-bit — best balance of size and quality

Training Approach

Same pipeline as Harmonic-9B. 799 curated rows — a small, precisely curated dataset instead of tens of thousands of unfiltered examples. The base model already has the knowledge from pretraining — the fine-tune teaches it a reasoning behavior pattern.

Every training row contains explicit self-correction ("wait, that's not right"), verification ("let me check by plugging back in"), and multi-path exploration ("alternatively, I could try..."). The data was generated from multiple frontier models and filtered through a custom structural quality pipeline that enforces reasoning depth, coherence, and flow patterns. 100% of rows pass all quality gates simultaneously.

Training Data Quality

The same reasoning data as Harmonic-9B and Harmonic-2B, curated using a custom structural process supervision pipeline:

Metric	Value
Signal quality score	78.7 mean (61.5 min, 90.0 max)
Thinking trace depth	1,667 words average
Self-correction	100% of rows (17.2 per row avg)
Verification	100% of rows (10.3 per row avg)
Exploration	100% of rows (6.3 per row avg)
Quality gate pass rate	100%

How It Compares

We ran our structural quality analysis against every major public reasoning dataset used for Opus/Qwen distillation. The results:

Dataset	Rows	Think Words	Self-Correction	Verification	Exploration	Signal Score	Gate Pass
Harmonic (ours)	799	1,667	100%	100%	100%	78.7	100%
Crownelius/Opus-3300x	2,160	188	5.9%	22.6%	5.2%	28.0	0.1%
nohurry/Opus-Filtered	2,326	191	6.7%	24.1%	5.3%	28.5	0.1%
TeichAI/Opus-250x	250	323	17.2%	26.8%	6.8%	24.6	0.4%
Jackrong/Qwen-700x	633	6,653	97.5%	97.6%	69.8%	75.6	22.7%
Bespoke-Stratos-17k	16,710	1,322	88.2%	72.7%	59.7%	71.7	49.0%
glaiveai/reasoning-20m	22M+	799	64.1%	41.4%	37.3%	46.2	12.8%
KingNish/reasoning-20k	19,944	132	0.7%	4.2%	4.3%	27.4	0.0%

Speculative Decoding

Harmonic-27B pairs with Harmonic-2B for speculative decoding. Both models share the same training data, reasoning format, and architecture family (Qwen 3.5), which keeps draft token acceptance rates high.

from transformers import AutoModelForCausalLM

target = AutoModelForCausalLM.from_pretrained("DJLougen/Harmonic-27B")
draft = AutoModelForCausalLM.from_pretrained("DJLougen/Harmonic-2B")

outputs = target.generate(
    **inputs,
    assistant_model=draft,
    max_new_tokens=512,
)

Usage

llama.cpp

llama-cli -m Harmonic-27B-Q4_K_M.gguf -p "What is the sum of the first 100 prime numbers?" -n 2048

Ollama

# Create a Modelfile
echo 'FROM ./Harmonic-27B-Q4_K_M.gguf' > Modelfile
ollama create harmonic-27b -f Modelfile
ollama run harmonic-27b

Reasoning format

The model uses think blocks for reasoning:

<|thinking|>
The user is asking about X. Let me consider two approaches...

Approach 1: ...
Approach 2: ...

I will go with Approach 1 because...

Wait, I need to be careful here - this assumes Y, which may not hold.
Let me verify by checking a special case...

Yes, that confirms the result.
<|/thinking|>

[Final answer here]

Training Configuration

base_model: unsloth/Qwen3.5-27B
dataset: 799 curated reasoning rows
epochs: 1
learning_rate: 1e-4
lr_scheduler: cosine
warmup_ratio: 0.1
max_seq_length: 8192
lora_rank: 32
lora_alpha: 32
dropout: 0.05
micro_batch_size: 1
gradient_accumulation_steps: 4
weight_decay: 0.01

Intended Use

Reasoning tasks requiring genuine multi-step thinking
Mathematical problem-solving with self-correction
Code analysis and generation with structured verification
General conversation (conversational ability preserved through training design)
Target model for speculative decoding with Harmonic-2B
Base model for Stage 2 agentic fine-tuning

Limitations

Reasoning traces can be verbose for simple questions
Not optimized for tool calling — see Harmonic-Hermes-9B for agentic use
Benchmark evaluation is ongoing

Architecture

Base: Qwen 3.5 27B (27.36B parameters)
Training: LoRA fine-tuning, merged into base weights
Precision: BF16 (original), quantized to F16/Q8_0/Q4_K_M
Context: 8192 tokens

License

Apache 2.0 — same as the base model. All training data is from Apache 2.0 or MIT licensed sources. Fully commercial use permitted.

Model tree for DJLougen/Harmonic-27B-GGUF

Base model

Qwen/Qwen3.5-27B

Finetuned

unsloth/Qwen3.5-27B