4-bit Autotrain compatible Awq Base model:q-bert/metamath-cyb... Base model:quantized:q-bert/me... Dataset:meta-math/metamathqa En Math Mistral Quantized Region:us Safetensors
Model Card on HF ๐ค: https://huggingface.co/TheBloke/MetaMath-Cybertron-Starling-AWQ
MetaMath Cybertron Starling AWQ Benchmarks
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)
๐ Advertise your project ๐
MetaMath Cybertron Starling AWQ Parameters and Internals
| LLM Name | MetaMath Cybertron Starling AWQ |
| Repository ๐ค | https://huggingface.co/TheBloke/MetaMath-Cybertron-Starling-AWQ |
| Model Name | Metamath Cybertron Starling |
| Model Creator | Talha Rüzgar Akkuล |
| Base Model(s) | |
| Model Size | 1.2b |
| Required VRAM | 4.2 GB |
| Updated | 2025-08-19 |
| Maintainer | TheBloke |
| Model Type | mistral |
| Model Files | |
| Supported Languages | en |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.35.2 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to MetaMath Cybertron Starling AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Feedback Wizard 4bit AWQ | 32K / 4.2 GB | 5 | 0 |
| Quantized Kheopss AWQ 4bits V1 | 32K / 4.2 GB | 17 | 0 |
| Ryze AWQ 4bit | 32K / 4.2 GB | 5 | 0 |
| ...V3 Plot Chat Roleplay Chat AWQ | 32K / 4.2 GB | 6 | 0 |
| ...lot Engine Step Json Short AWQ | 32K / 4.2 GB | 5 | 0 |
| MistralLite AWQ | 32K / 4.2 GB | 42 | 3 |
| MistralLite AWQ | 32K / 4.2 GB | 14 | 5 |
| Dictalm2.0 Instruct AWQ | 32K / 4.2 GB | 106 | 0 |
| Dictalm2.0 AWQ | 32K / 4.2 GB | 86 | 0 |
| SFR Embedding Mistral AWQ | 32K / 4.2 GB | 16 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/MetaMath-Cybertron-Starling-AWQ .
Rank the MetaMath Cybertron Starling AWQ Capabilities
๐ 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! ๐
What open-source LLMs or SLMs are you in search of? 50751 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124