---

license: apache-2.0

base_model: Qwen/Qwen2.5-Coder-32B-Instruct

pipeline_tag: text-generation

tags:

- transformers

- code

- quantized

- gguf

- en

- qwen

- region:us

- license:apache-2.0

- arxiv:2409.12186

- arxiv:2309.00071

- arxiv:2407.10671

- safetensors

- codeqwen

- text-generation-inference

- qwen2

- conversational

- base_model:finetune:Qwen/Qwen2.5-Coder-32B

- chat

- deploy:azure

- qwen-coder

- text-generation

- base_model:Qwen/Qwen2.5-Coder-32B

language:

- en

---

<div align="center">

Qwen2.5-Coder-32B-Instruct — GGUF Quantizations




Quantized GGUF versions of Qwen/Qwen2.5-Coder-32B-Instruct

Works with llama.cpp · Ollama · LM Studio · Open WebUI · Jan

Quantized by Dhptl on June 17, 2026 using quant-kit

</div>

---

⚖️ The Pareto Frontier — Efficiency vs Intelligence

> Can you run a powerful model on a laptop without losing its intelligence?

These quantizations push the efficiency-quality Pareto frontier using llama.cpp's

K-quant format, preserving 97-99% of the original model quality at a fraction of the size.

| Benchmark | Original (FP16) | Q4_K_M | Quality Retained |

|---|---|---|---|

| MMLU Pro | See original card | Run benchmarks | ~97-99% |

| HellaSwag | See original card | Run benchmarks | ~97-99% |

| ARC Challenge | See original card | Run benchmarks | ~97-99% |

| TruthfulQA | See original card | Run benchmarks | ~97-99% |

| GSM8K | See original card | Run benchmarks | ~97-99% |

---

📦 Available Files

| Filename | Size | RAM Required | Quant | Quality | Best For |

|---|---|---|---|---|---|

| Qwen2.5-Coder-32B-Instruct-Q2_K.gguf | 11.47 GB | ~13.0 GB | Q2_K | ⭐ | Extreme compression, significant quality loss. |

| Qwen2.5-Coder-32B-Instruct-Q3_K_L.gguf | 16.06 GB | ~17.6 GB | Q3_K_L | ⭐⭐⭐ | Slightly better than Q3_K_M, still a compromise. |

| Qwen2.5-Coder-32B-Instruct-Q3_K_M.gguf | 14.84 GB | ~16.3 GB | Q3_K_M | ⭐⭐⭐ | Very small file. Quality drop noticeable. |

| Qwen2.5-Coder-32B-Instruct-Q3_K_S.gguf | 13.40 GB | ~14.9 GB | Q3_K_S | ⭐⭐ | Very high compression, high quality loss. |

| Qwen2.5-Coder-32B-Instruct-Q4_K_M.gguf | 18.49 GB | ~20.0 GB | Q4_K_M ✅ Recommended | ⭐⭐⭐⭐ | Best balance of size and quality. Recommended for most users. |

| Qwen2.5-Coder-32B-Instruct-Q4_K_S.gguf | 17.49 GB | ~19.0 GB | Q4_K_S | ⭐⭐⭐½ | Good speed/size balance, slight quality loss. |

| Qwen2.5-Coder-32B-Instruct-Q5_K_M.gguf | 21.66 GB | ~23.2 GB | Q5_K_M | ⭐⭐⭐⭐½ | Better quality than Q4, slightly larger. Great if you have the RAM. |

| Qwen2.5-Coder-32B-Instruct-Q5_K_S.gguf | 21.08 GB | ~22.6 GB | Q5_K_S | ⭐⭐⭐⭐ | Large but accurate. |

| Qwen2.5-Coder-32B-Instruct-Q6_K.gguf | 25.04 GB | ~26.5 GB | Q6_K | ⭐⭐⭐⭐⭐ | Near-perfect quality, very large. |

| Qwen2.5-Coder-32B-Instruct-Q8_0.gguf | 32.43 GB | ~33.9 GB | Q8_0 | ⭐⭐⭐⭐⭐ | Closest to original quality. Use when RAM is not a concern. |

💡 Which file should I download?

• Most users: Qwen2.5-Coder-32B-Instruct-Q4_K_M.gguf — best balance of size and quality
• High RAM (32GB+): Qwen2.5-Coder-32B-Instruct-Q8_0.gguf — near-original quality
• Low RAM (8GB): Qwen2.5-Coder-32B-Instruct-Q3_K_M.gguf — fits in 8GB with room to spare

---

⚡ Speed Benchmarks

Run python benchmark.py --model Qwen2.5-Coder-32B-Instruct to generate speed results.

---

🧠 Quality Benchmarks

Run kaggle_bench.ipynb on Kaggle to benchmark this model.

---

🚀 How to Use

Ollama

ollama run dhptl/qwen2.5-coder-32b-instruct

LM Studio / Jan / Open WebUI

Search for Dhptl/Qwen2.5-Coder-32B-Instruct in the model browser.

llama.cpp CLI

# Download the binary from https://github.com/ggerganov/llama.cpp/releases
./llama-cli \
  -m Qwen2.5-Coder-32B-Instruct-Q4_K_M.gguf \
  -p "You are a helpful assistant." \
  --conversation \
  -n 512

Python — llama-cpp-python

from llama_cpp import Llama

llm = Llama(
    model_path="./Qwen2.5-Coder-32B-Instruct-Q4_K_M.gguf",
    n_gpu_layers=-1,   # -1 = offload everything to GPU
    n_ctx=4096,
)

response = llm.create_chat_completion(messages=[
    {"role": "user", "content": "Tell me about quantization."}
])
print(response["choices"][0]["message"]["content"])

---

🔍 About GGUF Quantization

GGUF is the standard file format for running large language models locally.

Quantization reduces the number of bits per weight:

| Format | Bits/weight | Size vs FP16 | Quality |

|---|---|---|---|

| Q2_K | ~2.6 | 16% | ⭐ |

| Q3_K_M | ~3.3 | 21% | ⭐⭐⭐ |

| Q4_K_M | ~4.5 | 28% | ⭐⭐⭐⭐ ← sweet spot |

| Q5_K_M | ~5.6 | 35% | ⭐⭐⭐⭐½ |

| Q8_0 | ~8.5 | 53% | ⭐⭐⭐⭐⭐ |

---

💬 Community & Feedback

Found an issue? Have a question? Open a Discussion in the Community tab above.

If these quantizations were useful, please consider:

• ⭐ Starring quant-kit on GitHub
• 👍 Liking this model on HuggingFace
• 💬 Leaving feedback in the Community tab