whatmodel.sh / Ring-flash-2.0
Ring-flash-2.0
↗ share
+ contribute
Ring-flash-2.0 is an open-weights language model from inclusionAI (Ant Group), released September 2025. Its published size is 100B parameters (6.1B active per token). Licence: mit.
Catalogue identity notes
Comparison-only. Arena entry 'ring-flash-2.0' (text). Maker repo inclusionAI/Ring-flash-2.0 @a73b44b: licence tag mit. Parameters: card: 'a total of 100B parameters, with only 6.1B activated per inference'. Released 2025-09: month the maker's Hugging Face repo was created (createdAt 2025-09-19). Thinking model built on Ling-flash-2.0-base; a separate checkpoint from Ling-flash-2.0.
$ how it compares
The LLMs ranked either side of Ring-flash-2.0, out of 1132 with a score, then more from inclusionAI (Ant Group).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 374 |  Athene-V2-Chat 72B | 56±2 | local | ||
| 375 |  Gemini 2.0 Flash Experimental | 56±1 | comparison only | ||
| 376 | Ring-flash-2.0 | 56±3 | local | ||
| 377 |  Sky-T1 32B Preview | 56±5 | local | ||
| 378 |  Qwen Plus (2025-01-25) | 56±1 | api $0.60/M | ||
| more from inclusionAI (Ant Group) | |||||
| 87 | Ling 3.0 Flash (124B-A5B) | 71±2 | api $0.090/M +local | ||
| 111 | Ring-2.6-1T | 69±2 | comparison only | ||
| 310 | Ling-flash-2.0 | 59±2 | local | ||
$ what it's good at
chat & writing▁▁▁▄▆▅▆█▆▆▆▂ #202 of 466 * · 95% of its score · 1 test
Beats Granite 4.2 8B, Qwen3-VL 30B-A3B Thinking, Mistral Small 4 (119B-A6.5B) here, though they rank higher overall. Trails LFM2.5 1.2B Instruct, LFM2.5 1.2B Thinking, Gemma 3 12B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena (text) | 1322.6 ✎ | ▁▁▁▂▃▃▃▆▆▇█▃ beats 158/379 | 95% |
$ 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 Ring-flash-2.0 · needs ~37.7 GB · from huggingface.co/mradermacherchat in the terminal
llama cli -hf mradermacher/Ring-flash-2.0-GGUF:Q2_K - Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf mradermacher/Ring-flash-2.0-GGUF:Q2_K
LM Studio
- Install LM Studio · Open the app once before using the lms command.
- Run Ring-flash-2.0 · needs ~37.7 GB · from huggingface.co/mradermacher
- Or download it in the terminal
lms get https://huggingface.co/mradermacher/Ring-flash-2.0-GGUF@Q2_K -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 Ring-flash-2.0 · needs ~37.7 GB · from huggingface.co/mradermacherchat in the terminal
ollama run hf.co/mradermacher/Ring-flash-2.0-GGUF:Q2_K
Other ways to run it
- Run it as published · needs ~205.78 GB, NVIDIA only · from github.com/vllm-project
vllm serve inclusionAI/Ring-flash-2.0
Official weights and documentation: huggingface.co/inclusionAI ↗
$ how the score was worked out · LMArena leaderboard dataset 95%
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 |
|---|---|---|
 LMArena leaderboard dataset | 1 | 95% |
| prior · pull toward the middle | 5% | |
| weighted average | = 56.2 |
$ 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