whatmodel.sh / LWM-Text-Chat-1M

LWM-Text-Chat-1M

+ contribute

LWM-Text-Chat-1M is an open-weights language model from Large World Model (UC Berkeley), released February 2024.

Catalogue identity notes

Maker repo LargeWorldModel/LWM-Text-Chat-1M @0598c44: no licence tag on the card. Released 2024-02: month the maker's Hugging Face repo was created (createdAt 2024-02-07).

42.1±5.1#665 of 949 LLMsfrom 2 benchmark results across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of LWM-Text-Chat-1M, out of 1132 with a score.

#	model	score	where	RAM	released
822	Mathstral 7B v0.1 Mistral AI	42±1	local	~5.8GB	2024-07
823	Yi-1.5 9B (base) 01.AI	42±2	local	~6.8GB	2024-05
824	LWM-Text-Chat-1M Large World Model (UC Berkeley)	42±5	local	~5.8GB	2024-02
825	Jais Family 6p7b (6.7B) Chat Inception (G42)	42±3	local	~32GB	2024-08
826	SILMA 9B Instruct v1.0 SILMA AI	42±3	local	~7.6GB	2024-08

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests2 not in a task · 88% of its score

test	result	vs the others in its run	difficulty	counts	why
RULER 64k	68.1% ✎	▁▁·▃·▂▃▄█▂·▁ beats 2/22	easy · avg 83%	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 67%	at its level
RULER 128k	65.0% ✎	▄··▂▄▂▆██▄▄▂ beats 8/21	easy · avg 68%	▇▇▇▇▇▇▇▇▇ 22%	at its level · noisy

$ 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 | sh
Windows
irm https://llama.app/install.ps1 | iex
other ways to install ↗
Run LWM-Text-Chat-1M · needs ~4.1 GB · from huggingface.co/mradermacher
chat in the terminal
llama cli -hf mradermacher/LWM-Text-Chat-1M-GGUF:Q4_K_M
Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf mradermacher/LWM-Text-Chat-1M-GGUF:Q4_K_M

LM Studio

version

Install LM Studio · Open the app once before using the lms command.
download it (macOS / Windows / Linux) ↗
Run LWM-Text-Chat-1M · needs ~4.1 GB · from huggingface.co/mradermacher
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/mradermacher/LWM-Text-Chat-1M-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) ↗
Linux
curl -fsSL https://ollama.com/install.sh | sh
Run LWM-Text-Chat-1M · needs ~4.1 GB · from huggingface.co/mradermacher
chat in the terminal
ollama run hf.co/mradermacher/LWM-Text-Chat-1M-GGUF:Q4_K_M

Other ways to run it

Run it as published · needs ~13.48 GB · from huggingface.co/LargeWorldModel (official)
uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='LargeWorldModel/LWM-Text-Chat-1M', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/LargeWorldModel ↗

$ how the score was worked out · NVIDIA RULER repository READM… 88%

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	licence
NVIDIA RULER repository README results table	2	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 88%	Apache-2.0
prior · pull toward the middle		▇▇▇ 12%
weighted average		= 42.1

$ improve this page

Update model information Add a place to run it Add a test result Propose a benchmark Correct a benchmark score Edit data on GitHub

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 2026-10-11 02:20 UTC · sources and licences · json