Hermes 4 14B 4bit is an open-source language model by mlx-community. Features: 14b LLM, VRAM: 8.3GB, Context: 40K, License: apache-2.0, Quantized, LLM Explorer Score: 0.23.
4-bit 4bit Atropos Base model:nousresearch/hermes... Base model:quantized:nousresea... Chat Chatml Conversational Dataforge En Finetuned Function calling Hybrid-mode Instruct Json mode Long context Mlx Quantized Qwen-3-14b Qwen3 Reasoning Region:us Roleplaying Safetensors Sharded Structured outputs Tensorflow Tool use
Model Card on HF 🤗: https://huggingface.co/mlx-community/Hermes-4-14B-4bit
Hermes 4 14B 4bit 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)
Hermes 4 14B 4bit Parameters and Internals
| LLM Name | Hermes 4 14B 4bit |
| Repository 🤗 | https://huggingface.co/mlx-community/Hermes-4-14B-4bit |
| Base Model(s) | |
| Model Size | 14b |
| Required VRAM | 8.3 GB |
| Updated | 2026-05-24 |
| Maintainer | mlx-community |
| Model Type | qwen3 |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | Qwen3ForCausalLM |
| License | apache-2.0 |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Transformers Version | 4.54.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Hermes 4 14B 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Prototie Ai | 40K / 29.5 GB | 346 | 0 |
| Qwen3 14B Unsloth Bnb 4bit | 40K / 11.2 GB | 200743 | 15 |
| Qwen3 14B MLX 4bit | 40K / 8.3 GB | 47678 | 5 |
| Qwen3 14B Bnb 4bit | 40K / 9.9 GB | 10231 | 4 |
| Qwen3 14B MLX 4bit | 40K / 7.9 GB | 2140 | 13 |
| ...wen3 14B Non Thinking V6 16bit | 40K / 29.5 GB | 18 | 0 |
| Merged16 Sft Qwen3 | 40K / 29.5 GB | 5 | 0 |
| Bee1reason Arabic Qwen 14B | 40K / 29.5 GB | 584 | 8 |
| Qwen3 14B 4bit DWQ 053125 | 40K / 8.3 GB | 432 | 6 |
| Qwen3 14B MLX 8bit | 40K / 15.2 GB | 518 | 5 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Hermes-4-14B-4bit .
Rank the Hermes 4 14B 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? 53999 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