LLM EXPLORER 61,755 MODELS INDEXED

Dolphin 2.6 Mixtral 8x7b GPTQ by TheBloke

By TheBloke · 12 downloads
HF Repo ↗ Copy URL

Dolphin 2.6 Mixtral 8x7b GPTQ is an open-source language model by TheBloke. Features: 46.7b LLM, VRAM: 23.8GB, Context: 32K, License: apache-2.0, MoE, Quantized, Instruction-Based, LLM Explorer Score: 0.1.

  4-bit Base model:dphn/dolphin-2.6-mi... Base model:quantized:dphn/dolp...   Conversational   Dataset:ehartford/dolphin Dataset:ehartford/dolphin-code... Dataset:ise-uiuc/magicoder-evo... Dataset:ise-uiuc/magicoder-oss... Dataset:jondurbin/airoboros-2....   Dataset:ldjnr/capybara   Dataset:teknium/openhermes   En   Gptq   Instruct   Mixtral   Moe   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/dolphin-2.6-mixtral-8x7b-GPTQ 

Dolphin 2.6 Mixtral 8x7b GPTQ Parameters and Internals

Model Type 
mixtral
Additional Notes 
The model is uncensored and should be used with caution as it is highly compliant. See developer's blog for more insights.
Supported Languages 
en (proficient)
Training Details 
Data Sources:
ehartford/dolphin, jondurbin/airoboros-2.2.1, ehartford/dolphin-coder, teknium/openhermes, ise-uiuc/Magicoder-OSS-Instruct-75K, ise-uiuc/Magicoder-Evol-Instruct-110K, LDJnr/Capybara
Methodology:
qLoRA and Axolotl
Context Length:
16000
Training Time:
3 days
Hardware Used:
4x A100 GPUs
Model Architecture:
Mixtral-8x7b with a 32k context updated to 16k
Input Output 
Input Format:
ChatML
Accepted Modalities:
text
Output Format:
text
LLM NameDolphin 2.6 Mixtral 8x7b GPTQ
Repository 🤗https://huggingface.co/TheBloke/dolphin-2.6-mixtral-8x7b-GPTQ 
Model NameDolphin 2.6 Mixtral 8X7B
Model CreatorCognitive Computations
Base Model(s)  cognitivecomputations/dolphin-2.6-mixtral-8x7b   cognitivecomputations/dolphin-2.6-mixtral-8x7b
Model Size46.7b
Required VRAM23.8 GB
Updated2026-08-04
MaintainerTheBloke
Model Typemixtral
Instruction-BasedYes
Model Files  23.8 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32002
Torch Data Typebfloat16

Best Alternatives to Dolphin 2.6 Mixtral 8x7b GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...ixtral 8x7B Instruct V0.1 GPTQ32K / 23.8 GB210141
Dolphin 2.5 Mixtral 8x7b GPTQ32K / 23.8 GB81114
...xtral Instruct 8x7b Zloss GPTQ32K / 23.8 GB72
....1 LimaRP ZLoss DARE TIES GPTQ32K / 23.8 GB56
Dolphin 2.7 Mixtral 8x7b GPTQ32K / 23.8 GB3219
...nstruct V0.1 LimaRP ZLoss GPTQ32K / 23.8 GB93
...tLM Mixtral 8x7B Instruct GPTQ32K / 23.8 GB393
... Mixtral 8x7b Instruct V3 GPTQ32K / 23.8 GB102
...ixtral 8x7B V0.1 Dolly15K GPTQ32K / 23.8 GB72
Mixtral 8x7B Instruct V0.132K / 93.6 GB8428934720
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/dolphin-2.6-mixtral-8x7b-GPTQ.