Model Intelligence Sheet
mondk/Claude-smolLM2-2B.gguf overview
It's a tiny model, but it's capable of tool calls—or so I guess thanks
Runs locally from ~1.70 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| slm2B-Q8_0.gguf | GGUF | Q8_0 | 1.70 GB | Download |
Model Details
| Model ID | mondk/Claude-smolLM2-2B.gguf |
|---|---|
| Author | mondk |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | mondk/claude-toolcall-slm-2B-safetensors |
| Last modified | 2026-09-10T09:37:27.000Z |
Model README
---
license: apache-2.0
datasets:
- mondk/claude-code-fable-5-traces.jsonl
- HuggingFaceTB/smollm-corpus
- bigcode/the-stack
- HuggingFaceTB/smoltalk
- openbmb/UltraFeedback
language:
- en
pipeline_tag: text-generation
tags:
- slm
- claude
- tool-call
base_model:
- mondk/claude-toolcall-slm-2B-safetensors
---
It's a tiny model, but it's capable of tool calls—or so I guess
thanks
Run mondk/Claude-smolLM2-2B.gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models