---

license: apache-2.0

base_model: jigs97022/minicpm5-2b-distilled-reasoning

tags:

- llama

- minicpm5

- gguf

- quantized

- text-generation

- reasoning

- distillation

- chain-of-thought

- qwen3.8-max

- glm-5.2

- kimi-k3

language:

- en

- zh

pipeline_tag: text-generation

library_name: gguf

---

minicpm5-2b-distilled-reasoning GGUF

GGUF quantizations of jigs97022/minicpm5-2b-distilled-reasoning.

A 2B parameter reasoning model distilled from three frontier models — Qwen3.8-Max, GLM-5.2, and Kimi K3 — onto the efficient openbmb/MiniCPM5-2B architecture.

Trained via QLoRA on 10,000 quality-filtered reasoning traces covering math, code, logic puzzles, and structured problem-solving.

---

Quantization Table

| File | Bits | Size | Use Case |

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

| model_f16.gguf | 16 | ~5.0 GB | Maximum quality, reference |

| model_q8_0.gguf | 8 | ~2.7 GB | Best quality / size tradeoff |

| model_q6_k.gguf | 6 | ~2.1 GB | High quality |

| model_q5_k_m.gguf | 5 | ~1.8 GB | Recommended |

| model_q5_k_s.gguf | 5 | ~1.7 GB | Slightly smaller Q5 |

| model_q4_k_m.gguf | 4 | ~1.5 GB | Good balance |

| model_q4_k_s.gguf | 4 | ~1.4 GB | Smaller Q4 |

| model_q3_k_l.gguf | 3 | ~1.2 GB | Low RAM, large variant |

| model_q3_k_m.gguf | 3 | ~1.1 GB | Low RAM |

| model_q3_k_s.gguf | 3 | ~1.0 GB | Minimum RAM Q3 |

| model_q2_k.gguf | 2 | ~0.8 GB | Extreme compression |

---

VRAM Requirements

| Quant | Min VRAM |

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

| F16 | 8 GB |

| Q8_0 | 4 GB |

| Q4_K_M | 2 GB |

| Q2_K | 1.5 GB |

---

Training Details

| Parameter | Value |

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

| Base Model | openbmb/MiniCPM5-2B |

| Teachers | Qwen3.8-Max, GLM-5.2, Kimi K3 |

| Dataset | r0b0tlab/qwen3.8-max-glm5.2-kimi-k3-distillation |

| Train Samples | 10,000 |

| Method | QLoRA (r=64, alpha=32) |

| Max Context | 4,096 tokens |

| Hardware | Kaggle T4 x2 |

---

Usage

llama.cpp

./llama-cli -m model_q4_k_m.gguf \
  --temp 0.7 \
  -n 1024 \
  -p "If 3x + 7 = 22, what is x? Show step-by-step reasoning."

llama-cpp-python

from llama_cpp import Llama

llm = Llama(model_path="model_q4_k_m.gguf", n_ctx=4096)
output = llm(
    "Solve step by step: If 3x + 7 = 22, what is x?",
    max_tokens=1024,
    temperature=0.7,
)
print(output["choices"][0]["text"])

LM Studio

Search tinyopsec/minicpm5-2b-distilled-reasoning-GGUF in the model browser.

Ollama

ollama run hf.co/tinyopsec/minicpm5-2b-distilled-reasoning-GGUF:Q4_K_M

---

Limitations

• Reasoning quality may degrade beyond 4K context
• Trained on 10K samples subset; edge cases may be weaker than full 52K variant
• English and Chinese only
• Knowledge cutoff ~2024 (inherited from MiniCPM5-2B base)

---

Original Model

jigs97022/minicpm5-2b-distilled-reasoning