whatmodel.sh / Dolphin 2.6 Mixtral 8x7B
Dolphin 2.6 Mixtral 8x7B
↗ share
+ contribute
Dolphin 2.6 Mixtral 8x7B is an open-weights language model from Cognitive Computations, released December 2023. Licence: apache-2.0.
Catalogue identity notes
Maker repo dphn/dolphin-2.6-mixtral-8x7b @db797db (requested as cognitivecomputations/dolphin-2.6-mixtral-8x7b, which the HF API redirects to dphn/dolphin-2.6-mixtral-8x7b): licence tag apache-2.0. Released 2023-12: month the maker's Hugging Face repo was created (createdAt 2023-12-21).
$ how it compares
The LLMs ranked either side of Dolphin 2.6 Mixtral 8x7B, out of 828 with a score, then more from Cognitive Computations.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 552 |  Xwin-LM 70B v0.1 | 44±1 | local | ||
| 553 |  Qwen3-VL 2B Instruct | 44±1 | local | ||
| 554 | Dolphin 2.6 Mixtral 8x7B | 44±1 | local | ||
| 555 |  Granite 8B Code Instruct (4K) | 44±1 | local | ||
| 556 |  Falcon3 10B Instruct | 44±3 | local | ||
| more from Cognitive Computations | |||||
| 673 | Dolphin 2.2.1 Mistral 7B | 37±2 | local | ||
$ what it's good at
coding▁▁▁▃▆██▇▆▄▃▁ #335 of 458 · 100% of its score · 3 tests
Beats GLM-4.7-Flash, LFM2.5 2.6B, LFM2.5 8B-A1B here, though they rank higher overall. Trails Phi-3-mini-128k-instruct (Apr 2024), DeepSeek LLM 67B Chat, WizardLM 70B V1.0 here, though they rank lower overall.
$ where to run it
llama.cpp · recommended
- Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.macOS / Linux
curl -LsSf https://llama.app/install.sh | shWindowsirm https://llama.app/install.ps1 | iex - Run Dolphin 2.6 Mixtral 8x7B · needs ~26.4 GB · from huggingface.co/dphn (official)chat in the terminal
llama cli -hf dphn/dolphin-2.6-mixtral-8x7b-GGUF:Q4_K_M - Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf dphn/dolphin-2.6-mixtral-8x7b-GGUF:Q4_K_M
LM Studio
- Install LM Studio · Open the app once before using the lms command.
- Run Dolphin 2.6 Mixtral 8x7B · needs ~26.4 GB · from huggingface.co/dphn (official)
- Or download it in the terminal
lms get https://huggingface.co/dphn/dolphin-2.6-mixtral-8x7b-GGUF@Q4_K_M -y - Then run lms ls to see its name, and lms chat followed by that name
Ollama
- Install Ollama
download it (macOS / Windows) ↗
Linuxcurl -fsSL https://ollama.com/install.sh | sh - Run Dolphin 2.6 Mixtral 8x7B · needs ~26.4 GB · from huggingface.co/dphn (official)chat in the terminal
ollama run hf.co/dphn/dolphin-2.6-mixtral-8x7b-GGUF:Q4_K_M
Other ways to run it
- Run it as published · needs ~93.41 GB · from huggingface.co/dphn (official)
uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='dphn/dolphin-2.6-mixtral-8x7b', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"
Official weights and documentation: huggingface.co/dphn ↗
$ how the score was worked out · EvalPlus / EvalPerf published… 100%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 EvalPlus / EvalPerf published evaluation runs | 3 | 100% |
| prior · pull toward the middle | 0% | |
| weighted average | = 43.9 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json