- Size
- 572B parameterscounted from the safetensors header on the Hub
- Licence
- unknown, MIT LicenseOur reading, check the licence: You can use, change and redistribute the model for any purpose, including commercially. Keep the copyright notice and the licence text with copies. You do not have to share your changes.
- On the Hub since
- 13 Oct 2026the date the repo was created
- Context length
- 256k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)BailingMoeV3ForCausalLM
- On Hugging Face
- inclusionAI/Ling-3.1-flash6.4k downloads in the last 30 days, 175 likes
Scores
No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.63 GB, worked out from the model's config (inclusionAI/Ling-3.1-flash), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
bartowski/Ling-3.1-flash-GGUF (converted by bartowski), 3.2k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| IQ3_XXS | 230.4 GBfile size, 7 parts | 231.5 GB230.4 + 0.63 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Ling-3.1-flash-GGUF:IQ3_XXSDownload hf download bartowski/Ling-3.1-flash-GGUF --include "Ling-3.1-flash-IQ3_XXS/Ling-3.1-flash-IQ3_XXS-*-of-00007.gguf" --local-dir Ling-3.1-flash-GGUF |
| IQ3_XS | 242.5 GBfile size, 7 parts | 243.6 GB242.5 + 0.63 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Ling-3.1-flash-GGUF:IQ3_XSDownload hf download bartowski/Ling-3.1-flash-GGUF --include "Ling-3.1-flash-IQ3_XS/Ling-3.1-flash-IQ3_XS-*-of-00007.gguf" --local-dir Ling-3.1-flash-GGUF |
| Q3_K_S | 243.6 GBfile size, 7 parts | 244.7 GB243.6 + 0.63 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Ling-3.1-flash-GGUF:Q3_K_SDownload hf download bartowski/Ling-3.1-flash-GGUF --include "Ling-3.1-flash-Q3_K_S/Ling-3.1-flash-Q3_K_S-*-of-00007.gguf" --local-dir Ling-3.1-flash-GGUF |
| Q3_K_M | 256.2 GBfile size, 7 parts | 257.3 GB256.2 + 0.63 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Ling-3.1-flash-GGUF:Q3_K_MDownload hf download bartowski/Ling-3.1-flash-GGUF --include "Ling-3.1-flash-Q3_K_M/Ling-3.1-flash-Q3_K_M-*-of-00007.gguf" --local-dir Ling-3.1-flash-GGUF |
| Q3_K_L | 268.2 GBfile size, 8 parts | 269.4 GB268.2 + 0.63 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Ling-3.1-flash-GGUF:Q3_K_LDownload hf download bartowski/Ling-3.1-flash-GGUF --include "Ling-3.1-flash-Q3_K_L/Ling-3.1-flash-Q3_K_L-*-of-00008.gguf" --local-dir Ling-3.1-flash-GGUF |
| IQ3_M | 276.9 GBfile size, 8 parts | 278.0 GB276.9 + 0.63 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Ling-3.1-flash-GGUF:IQ3_MDownload hf download bartowski/Ling-3.1-flash-GGUF --include "Ling-3.1-flash-IQ3_M/Ling-3.1-flash-IQ3_M-*-of-00008.gguf" --local-dir Ling-3.1-flash-GGUF |
| IQ4_XS | 295.3 GBfile size, 9 parts | 296.4 GB295.3 + 0.63 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Ling-3.1-flash-GGUF:IQ4_XSDownload hf download bartowski/Ling-3.1-flash-GGUF --include "Ling-3.1-flash-IQ4_XS/Ling-3.1-flash-IQ4_XS-*-of-00009.gguf" --local-dir Ling-3.1-flash-GGUF |
| Q4_0 | 304.2 GBfile size, 9 parts | 305.3 GB304.2 + 0.63 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Ling-3.1-flash-GGUF:Q4_0Download hf download bartowski/Ling-3.1-flash-GGUF --include "Ling-3.1-flash-Q4_0/Ling-3.1-flash-Q4_0-*-of-00009.gguf" --local-dir Ling-3.1-flash-GGUF |
| Q4_K_S | 313.5 GBfile size, 9 parts | 314.6 GB313.5 + 0.63 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Ling-3.1-flash-GGUF:Q4_K_SDownload hf download bartowski/Ling-3.1-flash-GGUF --include "Ling-3.1-flash-Q4_K_S/Ling-3.1-flash-Q4_K_S-*-of-00009.gguf" --local-dir Ling-3.1-flash-GGUF |
| Q4_K_M | 333.4 GBfile size, 10 parts | 334.5 GB333.4 + 0.63 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Ling-3.1-flash-GGUF:Q4_K_MDownload hf download bartowski/Ling-3.1-flash-GGUF --include "Ling-3.1-flash-Q4_K_M/Ling-3.1-flash-Q4_K_M-*-of-00010.gguf" --local-dir Ling-3.1-flash-GGUF |
| IQ4_NL | 333.4 GBfile size, 10 parts | 334.6 GB333.4 + 0.63 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Ling-3.1-flash-GGUF:IQ4_NLDownload hf download bartowski/Ling-3.1-flash-GGUF --include "Ling-3.1-flash-IQ4_NL/Ling-3.1-flash-IQ4_NL-*-of-00010.gguf" --local-dir Ling-3.1-flash-GGUF |
| Q4_1 | 335.4 GBfile size, 10 parts | 336.5 GB335.4 + 0.63 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Ling-3.1-flash-GGUF:Q4_1Download hf download bartowski/Ling-3.1-flash-GGUF --include "Ling-3.1-flash-Q4_1/Ling-3.1-flash-Q4_1-*-of-00010.gguf" --local-dir Ling-3.1-flash-GGUF |
| Q5_K_S | 378.2 GBfile size, 11 parts | 379.3 GB378.2 + 0.63 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Ling-3.1-flash-GGUF:Q5_K_SDownload hf download bartowski/Ling-3.1-flash-GGUF --include "Ling-3.1-flash-Q5_K_S/Ling-3.1-flash-Q5_K_S-*-of-00011.gguf" --local-dir Ling-3.1-flash-GGUF |
| Q5_K_M | 406.4 GBfile size, 12 parts | 407.5 GB406.4 + 0.63 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Ling-3.1-flash-GGUF:Q5_K_MDownload hf download bartowski/Ling-3.1-flash-GGUF --include "Ling-3.1-flash-Q5_K_M/Ling-3.1-flash-Q5_K_M-*-of-00012.gguf" --local-dir Ling-3.1-flash-GGUF |
| Q6_K_S | 445.9 GBfile size, 13 parts | 447.1 GB445.9 + 0.63 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Ling-3.1-flash-GGUF:Q6_K_SDownload hf download bartowski/Ling-3.1-flash-GGUF --include "Ling-3.1-flash-Q6_K_S/Ling-3.1-flash-Q6_K_S-*-of-00013.gguf" --local-dir Ling-3.1-flash-GGUF |
| Q6_K | 467.1 GBfile size, 14 parts | 468.3 GB467.1 + 0.63 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Ling-3.1-flash-GGUF:Q6_KDownload hf download bartowski/Ling-3.1-flash-GGUF --include "Ling-3.1-flash-Q6_K/Ling-3.1-flash-Q6_K-*-of-00014.gguf" --local-dir Ling-3.1-flash-GGUF |
| Q8_0 | 566.6 GBfile size, 16 parts | 567.7 GB566.6 + 0.63 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Ling-3.1-flash-GGUF:Q8_0Download hf download bartowski/Ling-3.1-flash-GGUF --include "Ling-3.1-flash-Q8_0/Ling-3.1-flash-Q8_0-*-of-00016.gguf" --local-dir Ling-3.1-flash-GGUF |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| F8_E4M3original weights | 534.2 GBfile size | 535.4 GB534.2 + 0.63 + 0.50 |
hf download inclusionAI/Ling-3.1-flash --local-dir Ling-3.1-flashOther conversions (4; sizes not read)
- Baekpica/Ling-3.1-flash-VQ-GGUF GGUF, 2.5k downloads
- bertholomus/Ling-3.1-flash-EXL3-3.03bpw EXL3, 308 downloads
- boxwrench/Ling-3.1-flash-exl3-wrench-2.10bpw EXL3, 121 downloads
- turboderp/Ling-3.1-flash-exl3 EXL3, 54 downloads
The Hub tags 8 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
1 provider serves this model through the Hugging Face router. Prices are US dollars per million tokens. Precision is what the provider reports; a lower precision than the original weights can change answers. Live first, then cheapest output.
| Provider | In | Out | Context | Precision | Tokens/s | First token | Uptime 24h | Tools | JSON |
|---|---|---|---|---|---|---|---|---|---|
| Novita | $0.045 | $0.14 | 977k | not given | 74 | 1.7 s | 100.0% | yes | no |
Through the router, with a Hugging Face token (the router bills your Hugging Face account). Change the name after the colon to pick another provider.
curl https://router.huggingface.co/v1/chat/completions \
-H "Authorization: Bearer $HF_TOKEN" -H "Content-Type: application/json" \
-d '{"model": "inclusionAI/Ling-3.1-flash:novita", "messages": [{"role": "user", "content": "Hello"}]}'Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.