Model Intelligence Sheet
qikp/MiniCPM5-1B-GGUF-imatrix overview
I took Abiray's F16 quantization https://huggingface.co/Abiray/MiniCPM5 1B GGUF , computed an imatrix using calibration data v3 https://gist.github.com/bartows…
Runs locally from ~1.3 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
6 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| MiniCPM5-1B-IQ4_XS.gguf | GGUF | IQ4_XS | 609.3 MB | Download |
| MiniCPM5-1B-Q3_K_M.gguf | GGUF | Q3_K_M | 555.9 MB | Download |
| MiniCPM5-1B-Q3_K_S.gguf | GGUF | Q3_K_S | 522.7 MB | Download |
| MiniCPM5-1B-Q4_K_M.gguf | GGUF | Q4_K_M | 656.2 MB | Download |
| MiniCPM5-1B-Q4_K_S.gguf | GGUF | Q4_K_S | 636.9 MB | Download |
| imatrix.gguf | GGUF | GGUF | 1.3 MB | Download |
Model Details
| Model ID | qikp/MiniCPM5-1B-GGUF-imatrix |
|---|---|
| Author | qikp |
| Pipeline | text-generation |
| License | — |
| Base model | Abiray/MiniCPM5-1B-GGUF |
| Last modified | 2026-07-08T06:49:59.000Z |
Model README
---
quantized_by: qikp
base_model: Abiray/MiniCPM5-1B-GGUF
pipeline_tag: text-generation
---
I took Abiray's F16 quantization, computed an imatrix using calibration data v3. It was whatever Claude suggested. Then, I quantized it to a few formats. Enjoy!
Run qikp/MiniCPM5-1B-GGUF-imatrix with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models