whatmodel.sh / TinyLlama 1.1B Chat v1.0
TinyLlama 1.1B Chat v1.0
↗ share
+ contribute
TinyLlama 1.1B Chat v1.0 is an open-weights language model from TinyLlama, released December 2023. Its published size is 1.1B parameters and a 2k-token context window. Licence: apache-2.0.
Catalogue identity notes
Maker repo TinyLlama/TinyLlama-1.1B-Chat-v1.0 @fe8a4ea: licence tag apache-2.0. 1,100,048,384 parameters from the Hugging Face safetensors metadata. Dense, so active = total. Released 2023-12: month the maker's Hugging Face repo was created (createdAt 2023-12-30). Ollama tags tinyllama:1.1b-chat-v1-q4_K_M, tinyllama:1.1b-chat-v1-q8_0 are the library's instruct/chat builds of this checkpoint (tag names on the pinned tags page); download sizes are estimated from the parameter count.
$ how it compares
The LLMs ranked either side of TinyLlama 1.1B Chat v1.0, out of 1132 with a score.
| # | model | score | where |
|---|---|---|---|
| 1086 |  Pythia 6.9B | 23±1 | local |
| 1087 |  OpenAssistant SFT-4 Pythia 12B | 22±1 | local |
| 1088 | TinyLlama 1.1B Chat v1.0 | 21±9 | local |
| 1089 | Pythia 2.8B | 21±1 | local |
| 1090 |  BLOOM 7.1B | 21±1 | local |
$ what it's good at
other tests1 not in a task · 67% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Open PT-LLM Leaderboard average (9 Portuguese tasks) | 28.2% ✎ | ▃▁▁▁▁▁▁▁▂█▅▁ beats 36/276 | 67% |
$ 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 TinyLlama 1.1B Chat v1.0 · needs ~0.7 GB · from huggingface.co/TheBlokechat in the terminal
llama cli -hf TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF:Q4_K_M - Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF:Q4_K_M
LM Studio
version
- Install LM Studio · Open the app once before using the lms command.
- Run TinyLlama 1.1B Chat v1.0 · needs ~0.7 GB · from huggingface.co/TheBloke
- Or download it in the terminal
lms get https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-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 TinyLlama 1.1B Chat v1.0 · needs ~1.16 GB · from ollama.comchat in the terminal
ollama run tinyllama:1.1b-chat-v1-q4_K_M
MLX (Mac)
version
- Install MLX (Mac) · Apple silicon Macs only, text only.with uv
uv tool install mlx-lmorpip install mlx-lm - Run TinyLlama 1.1B Chat v1.0 · needs ~0.6 GB, Mac only · from huggingface.co/pcuenqchat in the terminal
mlx_lm.chat --model pcuenq/TinyLlama-1.1B-Chat-v1.0-mlx - Or start an OpenAI-compatible server at http://localhost:8080/v1
mlx_lm.server --model pcuenq/TinyLlama-1.1B-Chat-v1.0-mlx
Official weights and documentation: huggingface.co/TinyLlama ↗
$ how the score was worked out · Open Portuguese LLM Leaderboa… 67%
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 | 67% |
| prior · pull toward the middle | 33% | |
| weighted average | = 21.4 |
$ 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