Qwen2.5-7B-Instruct · GGUF F16

Evaluation results: this F16 build is the baseline each quantized build of this model is measured against. Its pass rates by capability family, with confidence intervals, are on the results page: pbhappliedsystems.com/models/qwen2.5-7b-instruct#F16

How much does quantization degrade Qwen2.5-7B-Instruct?

Answer (quant_eval v7.22): this F16 build is the baseline. Against it:

• Q4_K_M degraded 2 of 8 families, improved 2 — Q4_K_M results

Licence provenance: Apache-2.0 (SPDX Apache-2.0), commercial use permitted_by_recorded_license; upstream Qwen/Qwen2.5-7B-Instruct at revision `` (unavailable_for_pre_provenance_legacy_artifact); evaluated file SHA-256 ebb1cb9f8d7721f5ea509ff9e7327873b039e523c17f2d03d6f1b90729574b54.

Other builds of this model: Q4_K_M · All evaluated builds (Collection) · Datasets

Contents: Model Description · PBH Applied Systems Evaluation — quant_eval v7.22.21 · Comparability & Fixture Methodology · Per-Family Pass Rates — Full-Weight Baseline · Key Findings · Quantization Variants Comparison · Artifact Provenance · Evaluation Methodology

Converted and evaluated by PBH Applied Systems, LLC — Applied AI/ML Consulting · LLM Optimization & Deployment · Quantized AI Infrastructure

🔬 This repository is part of a production-oriented evaluation series. Every model published under pbhappliedsystems has been independently evaluated using quant_eval v7.22.21/v7.22.22 — a behavioral evaluation harness developed by PBH Applied Systems. Scores measure real agent-adjacent task performance across structured output, tool dispatch, multi-turn state retention, and multi-step planning families — not perplexity or benchmark leaderboard proxies.

📌 This is the full-precision F16 baseline repository. The evaluated quantized variant is published separately: Q4_K_M. This card documents reference behavior. The quantized card shows how Q4_K_M compression impacts behavioral fidelity.

---

Try the Live AI Agent Demo & Compare Models

Two complementary interfaces, both free:

1. Quick Demo — Single Model Testing

Launch the PBH Applied Systems AI Agent Demo →

Free · 3 example queries per agent type · No account required · No document upload

Test this model (or others) against three agent workflow templates:

• Reasoning & Analysis — Chain-of-thought decomposition and structured problem-solving
  Example queries: Should a startup build on cloud LLMs or self-host quantized models? · Analyze the trade-offs between model quantization and inference latency. · What are the cost implications of running 7B parameter models on edge devices?

• Document Intelligence — Long-context information extraction and Q&A
  Example queries: Extract key clauses from a contract and summarize legal risks. · Analyze a research paper and identify the novel contributions. · Compare market analysis reports and highlight strategic differences.

• Code & Automation — API scaffolding, data transformation, and task completion
  Example queries: Build a REST API endpoint for user authentication and include rate limiting. · Transform CSV data into a production-ready database schema. · Write a Python script to validate and clean messy customer records.

Every query runs on private GPU infrastructure — your prompts, reasoning traces, and outputs never leave the system and are never sent to Frontier model providers or cloud vendors. This matters for organizations with sensitive data, compliance requirements, or internal knowledge that cannot leave the building.

2. Model Comparison Arena — Side-by-Side Evaluation

Launch the quant_eval Agent Arena Space →

Compare two models in real-time across all three agent types.

The Agent Arena lets you:

• Select any two evaluated models (F16 or quantized variants) and test them side-by-side on the same queries
• View execution traces for both agents, showing chain-of-thought reasoning and tool dispatch
• Check the Model Leaderboard — the Q4_K_M pass rate in each of the eight quant_eval capability families for every model with a published run, marked ▼ degraded or ▲ improved where McNemar's paired test against the model's own full-weight baseline is significant, ordered by how many families degraded
• Read the Methodology tab — explanation of quant_eval, the 8 test families, and how to request a full evaluation report for models not yet in the series

Why compare in the Arena:

The demo shows what this model can do. The Arena shows how this model compares to others. If you're deciding between F16 and Q4_K_M, or between this model and another in the series, run the same query in the Arena with both selected. You'll see the exact differences in reasoning quality, tool dispatch, and output coherence — not benchmark scores, but real agent behavior.

Evaluation-backed leaderboard: Every score in the Arena comes from published quant_eval results: the quant_eval Public Corpus (DOI 10.5281/zenodo.22009419) and, for showcase models such as Ministral-3-14B-Instruct-2512, sealed run bundles published as summaries. The numbers are not opinionated; they're measured.

---

Model Description

This repository contains the full-precision F16 GGUF of Qwen/Qwen2.5-7B-Instruct, a 7-billion parameter instruction-tuned model developed by Alibaba Qwen Team (2024). Qwen2.5-7B-Instruct features a 32,768-token context window and multilingual instruction-following capability.

The F16 format preserves all original float16 weights without quantization. In the PBH Applied Systems evaluation pipeline, the F16 variant serves as the reference baseline: it is evaluated first, then the quantized variant is evaluated against the same fixture set, enabling direct measurement of quantization impact on behavioral fidelity.

For most production deployments, the quantized variant (Q4_K_M) is the appropriate choice — offering substantial footprint and speed gains with controlled behavioral tradeoffs. The F16 is the right choice when full weight precision is required — particularly for hybrid answer+JSON responses, where F16 scores 1.000 vs Q4_K_M's 0.925.

Key Characteristics

• Parameters: 7B
• Format: GGUF F16 (full precision)
• File size: 15.2 GB
• SHA256: ebb1cb9f8d7721f5ea509ff9e7327873b039e523c17f2d03d6f1b90729574b54
• Context window: 32,768 tokens
• Minimum VRAM (GPU inference): ~17 GB
• Recommended GPU tier: RTX 4090 (24 GB) · A10G (24 GB)
• Inference speed (eval hardware): avg 55.44 tokens/sec on NVIDIA RTX 4090
• Multilingual: English, Chinese, and other languages

---

PBH Applied Systems Evaluation — quant_eval v7.22.21

Evaluation conducted by PBH Applied Systems, LLC using quant_eval v7.22.21 Run ID: Qwen2.5_7B_Instruct_20260814_234822 · Fixtures: v7.22.19 (SHA256: 2a0f7cdd...) Evaluation date: August 14, 2026 · Seed: 42 · Hardware: NVIDIA RTX 4090 · Published: August 15, 2026

Evaluation Data Published to Zenodo

All evaluation artifacts are published under the quant_eval Public Corpus (DOI: 10.5281/zenodo.22009419):

• Run Provenance (D4): 10.5281/zenodo.22010462 — Selected run manifest and rollup fields, artifact SHA-256 hashes, runner and decoding configurations
• Golden Oracle Fixtures (D3): 10.5281/zenodo.22010278 — Test case specifications and fixture version crosswalk
• Family Pass Rates (D6): 10.5281/zenodo.22010623 — Aggregate pass rates per family, both runners, 95% Wilson confidence intervals
• Per-Case Behavioral Results (D1): 10.5281/zenodo.22009799 — 19,200 per-case rows, both precisions, all signals, case-level pass/fail
• Throughput Telemetry (D2): 10.5281/zenodo.22009987 — Per-call generation metrics, wall-time, token counts
• Efficiency & Footprint (D7): 10.5281/zenodo.22010723 — Stored artifact size, compression ratio, tokens/sec, observed wall-time ratios with hardware scope

Evaluation Contract: canonical_agentic_contract_v7.22.17:evaluation

---

Comparability & Fixture Methodology

Fixtures Enable Valid Variant Comparison

The quant_eval evaluation harness uses a consistent fixture set to measure both full-precision and quantized variants. The F16 and Q4_K_M variants were evaluated under the same fixture set, enabling direct comparison.

Fixture Generation:

What this means: Results are directly comparable. Both runners used identical fixtures, enabling precise measurement of Q4_K_M degradation relative to F16.

---

Per-Family Pass Rates — Full-Weight Baseline

All rates include 95% Wilson score confidence intervals. N = 200 cases per family.

Source: quant_eval Family Pass Rates, DOI 10.5281/zenodo.22010623

---

Key Findings

Finding 1: Hybrid Responses Clean; Tool Selection Is the Weak Point

Qwen2.5-7B at full precision demonstrates perfect performance on hybrid responses (1.000). The hybrid family measures simultaneous natural-language and JSON correctness — a non-trivial capability that this model executes flawlessly. Tool dispatch is weaker: toolcall_only reaches 0.805, and all 39 failures are tool-name selection errors — argument construction passes on all 200 cases. End-to-end toolcall (0.710) shows the same pattern: all 58 failures are selection failures.

Finding 2: Multi-Step Planning — Difficult Task Even at F16

The json_multistep family tests multi-step planning, and at full precision this model achieves only 0.355 pass rate — below 40%. This reflects the model's inherent limitations on autonomous multi-step reasoning, not a precision artifact. Planning tasks benefit from external scaffolding (ReAct, hierarchical composition) rather than end-to-end autonomy at this model size.

Finding 3: Stateful Conversation — Three-Quarters Success

Stateful execution reaches 0.750, meaning one in four two-turn conversations fail on turn-2 state tracking. For applications requiring perfect state retention, this rate requires retry logic or validation. For general conversation, 75% success is usable but not enterprise-grade.

---

Quantization Variants Comparison

See how this model performs across the quantized variant. All evaluated under the same fixture set.

How to read this table: Speed is the observed evaluation wall-time ratio (F16 ÷ quantized) on the same RTX 4090 — not a controlled throughput benchmark. Generation throughput ratio for the same pair is 2.15× (55.44 → 119.12 tokens/sec).

See the full Q4_K_M card:

• Q4_K_M — Significant gains in two families (json_multistep, stateful_followup) and significant losses in two (mixed_brief_json, json)

---

Artifact Provenance

The artifact was produced from Qwen/Qwen2.5-7B-Instruct using a custom-built llama.cpp conversion pipeline developed by PBH Applied Systems, without modification to model weights.

Artifact verification: SHA256 hashes are recorded in the run manifest (DOI 10.5281/zenodo.22010462). Download the F16 GGUF and verify:

sha256sum Qwen2.5_7B_Instruct_F16.gguf
# Should output: ebb1cb9f8d7721f5ea509ff9e7327873b039e523c17f2d03d6f1b90729574b54

---

Evaluation Methodology

quant_eval v7.22.21 is a behavioral evaluation harness developed by PBH Applied Systems. The two-run architecture evaluates the full-precision (F16) model first, then evaluates the quantized variant against the same fixture set, enabling direct measurement of behavioral degradation.

Fixture set: v7.22.19 evaluation split

• Total unique cases: 1,600 (200 per family × 8 families)
• Per-family test families and pass signals:

Evaluation hardware: NVIDIA RTX 4090 (24 GB VRAM) Runner: full_weight_llama_cpp (llama.cpp via Python binding, version 0.3.16) Decoding: temperature 0.7, seed 42, top_p 1.0 Context: 4,096-token context window (llama.cpp configuration) Reproducibility: Run manifest, fixtures, and per-case results published to Zenodo under the quant_eval Public Corpus

---

Deployment Recommendations

✅ Deploy F16 when:

• Hybrid responses are central. F16 scores 1.000 on mixed_brief_json; Q4_K_M drops to 0.925 (McNemar p = 6.1e−05).
• Full weight precision is required. Note: this evaluation ran at a 4,096-token context; long-context behavior at either precision was not measured.
• You have enterprise GPU tier. A10G, RTX 4090, or dual T4.

⚠️ Avoid F16 if:

• Latency is the bottleneck. On the same RTX 4090, Q4_K_M achieves 2.15× generation throughput (1.98× observed wall-time) while improving stateful execution (0.750 → 0.870).
• Hardware is constrained to <17 GB VRAM. Q4_K_M fits in ~7 GB.
• Cost efficiency matters. 69% footprint reduction; significant losses are limited to hybrid responses (−0.075) and single-step JSON (−0.045).

---

About PBH Applied Systems

PBH Applied Systems, LLC is an Oklahoma City–based applied machine learning and AI systems company specializing in production-grade model evaluation, quantization pipelines, agentic AI infrastructure, and scalable AI-driven application development. The organization emphasizes engineering rigor, reproducibility, and real-world deployment constraints — particularly in environments where performance, cost efficiency, and reliability must be balanced against available hardware and budget.

Founder & Principal AI/ML Systems Architect — Patrick Hill

Patrick Hill is the Founder & Principal AI/ML Systems Architect of PBH Applied Systems with 10+ years of experience delivering advanced analytics, predictive modeling, and decision-support solutions across high-stakes operational environments. Patrick holds a Master of Science in Software Engineering with concentrations in Artificial Intelligence and Machine Learning and a B.S. in Business Finance.

Technical expertise spans: Python, SQL, Linux, Pandas, NumPy, scikit-learn, PyTorch, TensorFlow/Keras, HuggingFace Transformers, GGUF, llama.cpp, BitsAndBytes, PEFT, QLoRA, Flask APIs, Docker, CI/CD, Jupyter, Databricks, and quantization strategies.

Published Author: Patrick is the author of Applied Machine Learning: Concepts, Tools, and Case Studies — a 1,200+ page practitioner-oriented textbook adopted as required reading for CSC 373 – Machine Learning at the University of Advancing Technology.

Core Service Areas: LLM optimization & deployment · AI evaluation frameworks · Agentic AI infrastructure · Scalable AI application development · ML pipeline design & analytics · Model & agent cataloging.

---

🔬 About quant_eval & This Evaluation Series

quant_eval is a behavioral evaluation harness developed by PBH Applied Systems, LLC. It measures real agent-adjacent task performance across structured output, tool dispatch, multi-turn state retention, and multi-step planning — not perplexity or leaderboard proxies. Every model published under pbhappliedsystems has been independently evaluated using quant_eval before being recommended for any production role.

See it in action: Live AI Agent Demo →

---

📋 Interested in Deeper Engagement?

This model card documents behavioral evidence under quant_eval. If you're evaluating this model for production deployment, need guidance on quantization impact for your specific workload, or want to understand deployment tradeoffs under your infrastructure constraints, PBH Applied Systems offers several paths:

Async Intake Form — https://pbhappliedsystems.com/contact

Describe your use case, infrastructure, and evaluation needs. Responses are reviewed asynchronously.

Available Services:

• Evaluation Report — A written behavioral audit: per-family pass rates, F16 vs. quantized delta analysis, failure cluster diagnostics, deployment recommendation, and a quantization-level suggestion for your hardware and latency constraints. Evidence-standard numbers only. Typical engagements: $2,500–$5,000.

• Sample report — Read a complete sample report: a real evaluation report for Ministral-3-14B-Instruct-2512, its BF16 baseline against Q4_K_M, Q5_K_M and Q8_0, written exactly as a client receives it.

• Starter-Kit Recommender — Configured agent templates (reasoning, document intelligence, code automation) with proof metrics from your specific workload. Includes model selection, quantization strategy, and deployment architecture guidance tied to your infrastructure.

Submit your details via the form above, and we'll route you to the appropriate engagement.

---

💬 Community

Questions about this model, a model or quant you want measured next, or your own quantization results to compare:

• Discord — PBH Applied Systems: #model-requests, #your-evals, #deployment-help
• GitHub Discussions — quant_eval Public Corpus tools: model requests and polls on what to measure next
• This repo — the Community tab for anything specific to these files

---

License

This GGUF repository inherits the license of the base model: Apache 2.0 — Qwen/Qwen2.5-7B-Instruct

The quant_eval evaluation harness, fuzz prompt builder, and scoring implementation are proprietary to PBH Applied Systems, LLC and are not included in this repository. The golden oracle fixture set used in this evaluation is published under CC BY 4.0 as part of the quant_eval Public Corpus (D3, DOI 10.5281/zenodo.22010278).

---

GGUF conversion and behavioral evaluation performed by PBH Applied Systems, LLC · quant_eval v7.22.21 · Run ID: Qwen2.5_7B_Instruct_20260814_234822 · Published 2026-08-15