Rho Math 1B V0.1 4bit is an open-source language model by mlx-community. Features: 1b LLM, VRAM: 0.7GB, Context: 2K, License: mit, Quantized, HF Score: 35, LLM Explorer Score: 0.17, Arc: 34.3, HellaSwag: 53.3, MMLU: 27.1, TruthfulQA: 35.5, WinoGrande: 59.8.
Model Card on HF 🤗: https://huggingface.co/mlx-community/rho-math-1b-v0.1-4bit
Rho Math 1B V0.1 4bit Benchmarks
ARC: 34.3 vs 96.7 (so35)-64.5%
HellaSwag: 53.34 vs 95.3 (gpt4)-44%
MMLU: 27.05 vs 88.3 (so35)-69.4%
TruthfulQA: 35.48 vs 59 (gpt4)-39.9%
WinoGrande: 59.75 vs 87.5 (gpt4)-31.7%
LLME Score: 0.17244
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Rho Math 1B V0.1 4bit Parameters and Internals
| Model Type |
| |
| Additional Notes |
| |
| Supported Languages |
|
| LLM Name | Rho Math 1B V0.1 4bit |
| Repository 🤗 | https://huggingface.co/mlx-community/rho-math-1b-v0.1-4bit |
| Base Model(s) | |
| Model Size | 1b |
| Required VRAM | 0.7 GB |
| Updated | 2026-03-18 |
| Maintainer | mlx-community |
| Model Type | llama |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | LlamaForCausalLM |
| License | mit |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.39.3 |
| Vocabulary Size | 32000 |
| Torch Data Type | float32 |
Best Alternatives to Rho Math 1B V0.1 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| CodeNexus | 128K / 2.5 GB | 62 | 0 |
| ...2 1B Instruct Unsloth Bnb 4bit | 128K / 1.1 GB | 101952 | 4 |
| Llama 3.2 1B Instruct 4bit | 128K / 0.7 GB | 122614 | 19 |
| Llama 3.2 1B Unsloth Bnb 4bit | 128K / 1.1 GB | 11108 | 2 |
| Llama 3.2 1B Instruct Bnb 4bit | 128K / 1 GB | 30686 | 22 |
| Llama 3.2 1B Bnb 4bit | 128K / 1 GB | 20630 | 15 |
| Orca Mini V9 5 1B Instruct | 128K / 2.5 GB | 7 | 4 |
| Llama Deepsync 1B | 128K / 2.5 GB | 22 | 3 |
| Llama 3.2 1B Instruct Chat Sft | 128K / 2.5 GB | 6 | 0 |
| Orca Mini V9 1 1B Instruct | 128K / 2.5 GB | 77 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/rho-math-1b-v0.1-4bit .
Rank the Rho Math 1B V0.1 4bit Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 52509 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a