Dolphin 2.8 Experiment26 7B AWQ is an open-source language model by solidrust. Features: 7b LLM, VRAM: 4.2GB, Context: 32K, License: apache-2.0, Quantized, HF Score: 68.6, LLM Explorer Score: 0.13, Arc: 64.5, HellaSwag: 83.8, MMLU: 63.2, TruthfulQA: 54.9, WinoGrande: 81.6, GSM8K: 63.6.
4-bit Autotrain compatible Awq Base model:dphn/dolphin-2.8-ex... Base model:quantized:dphn/dolp... Conversational Dataset:ehartford/dolphin Dataset:ehartford/dolphin-code... Dataset:jondurbin/airoboros-2.... Dataset:m-a-p/code-feedback Dataset:teknium/openhermes En Endpoints compatible Mistral Pytorch Quantized Region:us Safetensors Text-gen
Model Card on HF 🤗: https://huggingface.co/solidrust/dolphin-2.8-experiment26-7b-AWQ
Dolphin 2.8 Experiment26 7B AWQ Benchmarks
ARC: 64.51 vs 96.7 (so35)-33.3%
HellaSwag: 83.79 vs 95.3 (gpt4)-12.1%
MMLU: 63.24 vs 88.3 (so35)-28.4%
TruthfulQA: 54.87 vs 59 (gpt4)-7%
WinoGrande: 81.61 vs 87.5 (gpt4)-6.7%
GSM8K: 63.61 vs 96.4 (so35)-34%
LLME Score: 0.13423
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)
Dolphin 2.8 Experiment26 7B AWQ Parameters and Internals
| LLM Name | Dolphin 2.8 Experiment26 7B AWQ |
| Repository 🤗 | https://huggingface.co/solidrust/dolphin-2.8-experiment26-7b-AWQ |
| Model Name | ChatHercules-2.5-Mistral-7B |
| Model Creator | hydra-project |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 4.2 GB |
| Updated | 2026-04-07 |
| Maintainer | solidrust |
| 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 | 4.38.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32002 |
| Torch Data Type | float16 |
Best Alternatives to Dolphin 2.8 Experiment26 7B AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mistral 7B Instruct V0.2 AWQ | 32K / 4.2 GB | 5 | 0 |
| Mistral 7B Instruct V0.2 AWQ | 32K / 4.2 GB | 375775 | 52 |
| Mistral 7B Instruct V0.3 AWQ | 32K / 4.2 GB | 3381 | 9 |
| Ghost 7B Alpha AWQ | 32K / 4.2 GB | 6 | 0 |
| Tess 7B V2.0 AWQ | 32K / 4.2 GB | 5 | 1 |
| ...reeze 7B 32K Instruct V1.0 AWQ | 32K / 4.7 GB | 9 | 0 |
| Breeze 7B Instruct V1.0 AWQ | 32K / 4.6 GB | 6 | 0 |
| Mahou 1.3a Mistral 7B AWQ | 32K / 4.2 GB | 2 | 1 |
| Mahou 1.3 Mistral 7B AWQ | 32K / 4.2 GB | 7 | 0 |
| NSFW DPO Noromaid 7B AWQ | 32K / 4.2 GB | 3 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than solidrust/dolphin-2.8-experiment26-7b-AWQ .
Rank the Dolphin 2.8 Experiment26 7B AWQ 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? 52758 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