---

license: apache-2.0

base_model: GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking

base_model_relation: quantized

language:

- en

- zh

pipeline_tag: text-generation

library_name: gguf

tags:

- gguf

- llama.cpp

- quantized

- minicpm5

- thinking

- fable5

- tool-calling

- function-calling

- coding

- instruction-following

- conversational

---

<p align="center">

<img src="assets/banner.png" alt="MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-GGUF" width="100%"/>

</p>

MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-GGUF

GGUF quantizations of MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking for llama.cpp, Ollama, LM Studio, jan, KoboldCpp, and other GGUF runtimes.

中文说明

This repository provides local-deployment builds of a 1B Thinking model fine-tuned on Fable 5 data (V2) atop openbmb/MiniCPM5-1B. Compared with V1, V2 strengthens tool calling / function calling, while keeping MiniCPM5's native chat template embedded in the GGUF files.

Transformers checkpoint: MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking

Previous GGUF version: MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF (V1)

---

Files

| File | Quant | Size | Notes |

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

| MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-Q8_0.gguf | Q8_0 | ~1.1 GB | recommended default |

| MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-F16.gguf | F16 | ~2.1 GB | full-precision conversion base |

Q8_0 is the recommended default quant for this 1B model.

---

Quick start

llama.cpp (llama-cli)

llama-cli \
  -m MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-Q8_0.gguf \
  -p "Write a Python function to merge two sorted lists." \
  -n 512 \
  --temp 0.9 --top-p 0.95 \
  -c 8192

> The model supports up to 128K tokens (131,072) per config.json. Set -c according to your available VRAM/RAM.

llama.cpp server

llama-server \
  -m MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-Q8_0.gguf \
  -c 8192 --port 8080

LM Studio / jan / KoboldCpp

Load any .gguf file from this repository. The MiniCPM5 chat template is embedded in the GGUF metadata.

---

Sampling recommendations

Generation defaults are inherited from MiniCPM5-1B:

| Mode | Params |

|---|---|

| Think (default) | temperature=0.9, top_p=0.95 |

| No Think | temperature=0.7, top_p=0.95, enable_thinking=False |

---

Capabilities

• Tool calling (enhanced in V2) — stronger function-calling / tool-use behavior
• Fable 5 fine-tune (V2) — post-trained on Fable 5 data
• Coding — code generation, debugging, and software-engineering workflows
• Instruction following — more reliable adherence to user prompts and task constraints
• Thinking mode — chain-of-thought reasoning; MiniCPM5 chat template baked into the GGUF
• Long context — up to 128K tokens (131,072 tokens per upstream config.json)

---

Benchmark

Scores for the Transformers checkpoint MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking:

BFCL + API-Bank

| Model | BFCL non_live | BFCL live | API-Bank |

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

| MiniCPM5-1B (Base) | 41.51% | 60.24% | 7.30% |

| MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking | 43.06% | 63.33% | 22.10% |

Tau-Bench

| Domain | MiniCPM5-1B (Base) | MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking |

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

| Airline | 0.34 (17/50) | 0.36 (18/50) |

| Retail | 0.052 (6/115) | 0.070 (8/115) |

---

Limitations

• Thinking outputs — the model may emit reasoning blocks before the final answer
• 1B scale — lightweight local deployment; not frontier-scale
• Runtime context — actual usable context depends on your GGUF runtime and hardware limits

---

Provenance & licensing

Apache-2.0, inherited from MiniCPM5-1B.

Acknowledgements

• Base model: OpenBMB / MiniCPM5-1B
• Transformers checkpoint: MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking
• Quantization: llama.cpp