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

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

GGUF quantizations of MiniCPM5-1B-Claude-Opus-Fable5-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 atop openbmb/MiniCPM5-1B. The GGUF files embed MiniCPM5's native chat template for llama.cpp-compatible runtimes.

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

Files

File Quant Size Notes
MiniCPM5-1B-Claude-Opus-Fable5-Thinking-Q4_K_M.gguf Q4_K_M ~657 MB smallest footprint
MiniCPM5-1B-Claude-Opus-Fable5-Thinking-Q5_K_M.gguf Q5_K_M ~751 MB balanced quality / size
MiniCPM5-1B-Claude-Opus-Fable5-Thinking-Q8_0.gguf Q8_0 ~1.1 GB recommended default
MiniCPM5-1B-Claude-Opus-Fable5-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-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-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

  • Fable 5 fine-tune — 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)

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