whatmodel.sh / Neural Chat 7B v3.3
Neural Chat 7B v3.3
↗ share
+ contribute
Neural Chat 7B v3.3 is an open-weights language model from Intel, released December 2023. Its published size is 7.24B parameters. Licence: apache-2.0.
Catalogue identity notes
Maker repo Intel/neural-chat-7b-v3-3 @7506dfc: licence tag apache-2.0. 7,241,732,096 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2023-12: month the maker's Hugging Face repo was created (createdAt 2023-12-09).
$ how it compares
The LLMs ranked either side of Neural Chat 7B v3.3, out of 1132 with a score.
| # | model | score | where |
|---|---|---|---|
| 592 |  Llama-3-70B-Instruct-Gradient-1048k | 50±6 | local |
| 593 |  Mistral Small Instruct 22B (2409) | 49±2 | local |
| 594 | Neural Chat 7B v3.3 | 49±6 | local |
| 595 |  Qwen2-Math 72B Instruct | 49±1 | local |
| 596 |  OLMo 2 32B Instruct (0325) | 49±1 | local |
$ what it's good at
other tests2 not in a task · 85% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Open PT-LLM Leaderboard average (9 Portuguese tasks) | 67.1% ✎ | ▃▁▁▁▁▁▁▁▂█▅▁ beats 132/276 | 66% |
| Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate) | 97.4% ✎ | ▁▁▂▃▄▄█▆▃▂▂▁ beats 112/140 | 19% |
$ where to run it
llama.cpp · recommended
version
- 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 Neural Chat 7B v3.3 · needs ~4.4 GB · from huggingface.co/TheBlokechat in the terminal
llama cli -hf TheBloke/neural-chat-7B-v3-3-GGUF:Q4_K_M - Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf TheBloke/neural-chat-7B-v3-3-GGUF:Q4_K_M
LM Studio
version
- Install LM Studio · Open the app once before using the lms command.
- Run Neural Chat 7B v3.3 · needs ~4.4 GB · from huggingface.co/TheBloke
- Or download it in the terminal
lms get https://huggingface.co/TheBloke/neural-chat-7B-v3-3-GGUF@Q4_K_M -y - Then run lms ls to see its name, and lms chat followed by that name
Ollama
version
- Install Ollama
download it (macOS / Windows) ↗
Linuxcurl -fsSL https://ollama.com/install.sh | sh - Run Neural Chat 7B v3.3 · needs ~4.4 GB · from huggingface.co/TheBlokechat in the terminal
ollama run hf.co/TheBloke/neural-chat-7B-v3-3-GGUF:Q4_K_M
Other ways to run it
- Run it as published · needs ~14.48 GB · from huggingface.co/Intel (official)
uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='Intel/neural-chat-7b-v3-3', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"
Official weights and documentation: huggingface.co/Intel ↗
$ how the score was worked out · Open Portuguese LLM Leaderboa… 66%, Vectara hallucination leaderb… 19%
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 |
|---|---|---|
 Open Portuguese LLM Leaderboard (archived) | 1 | 66% |
 Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository) | 1 | 19% |
| prior · pull toward the middle | 15% | |
| weighted average | = 49.4 |
$ 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