Ling-3.0-flash
- In Input modalities: Text Out Output modalities: Text
- Reasoning
- Reasoning can be off
- Tool use
- Open weights
Prices
1 offering · prices as listedLing-3.0-flash| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard | ¥0.50 | ¥0.10 | ¥1.50 |
Prices from Ant Ling: model pricing (opens in a new tab) (checked Nov 4, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Licence
- mit
- Family
- ling-flash
- Model ID
Not stated on Ant Group’s pages: max input, reasoning efforts, max thinking budget, structured output, built-in tools, knowledge cutoff, aliases.
Run locally
Weights: inclusionAI/Ling-3.0-flash- Parameters 127.5B
- Active 5.1B · 512 experts, 8 per token
- Native precision BF16
- Layers 42
- KV cache per token 47 KB
- Config positions 256K (config.json max_position_embeddings)
- API context 250K (maker’s API)
- Needs
- ≈ 75.7 GB (weights 71.7 (maker’s file) + KV cache 0.4 + overhead 3.6)
- Usable
- 21.6 GB (90% of its memory)
- In system memory
- 54.6 GB · 10/42 layers on the GPU (--n-gpu-layers 10)
- Generation speed
- 19–28 tok/s (reads the active 5.1B per token)
- First token
- about 0.16–0.25 s for a 2K prompt
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| BF16 (native)maker’s file | 237.5 GB | ≈ 249.7 | ✕Doesn’t fit | — |
| Q8_0maker’s file | 126.3 GB | ≈ 133.0 | ✕Doesn’t fit | — |
| FP8maker’s file | 119.6 GB | ≈ 126.0 | ✕Doesn’t fit | — |
| Q6_Kmaker’s file | 97.6 GB | ≈ 102.8 | ✕Doesn’t fit | — |
| Q5_K_Mmaker’s file | 84.3 GB | ≈ 88.8 | ✕Doesn’t fit | — |
| Q5_0 | 81.6 GB | ≈ 86.1 | ✕Doesn’t fit | — |
| Q4_K_Mmaker’s file | 71.7 GB | ≈ 75.7 | ○Needs system memory 19–28 tok/s | — |
| Q4_0 | 66.8 GB | ≈ 70.5 | ○Needs system memory 21–31 tok/s | — |
| INT4 (AWQ / GPTQ)maker’s file | 71.7 GB | ≈ 75.7 | ○Needs system memory 19–28 tok/s | — |
| IQ4_XS | 63.1 GB | ≈ 66.6 | ○Needs system memory 22–34 tok/s | — |
| Q3_K_Mquality drops | 58.0 GB | ≈ 61.3 | ○Needs system memory 41–62 tok/s | — |
| IQ3_XXSquality drops | 45.4 GB | ≈ 48.1 | ○Needs system memory 53–79 tok/s | — |
| Q2_Kquality drops | 44.5 GB | ≈ 47.1 | ○Needs system memory 54–81 tok/s | — |
| IQ2_XXSquality drops | 30.6 GB | ≈ 32.5 | ○Needs system memory 82–124 tok/s | — |
Click a row to choose a precision. “Maker’s file” sizes are the maker’s own files; others are parameters × bits per weight.
Compared with other hardware
Each at the highest precision it runs. Click one for details.
Smallest that runs it (Q4_K_M, 8K): GPU NVIDIA RTX PRO 6000 Blackwell Workstation Edition; unified memory Apple M5 Max (40-core GPU) · 128 GB.
Run commands
llama-server -hf inclusionAI/Ling-3.0-flash-GGUF:Q4_K_M -c 8192 --n-gpu-layers 10
ollama run hf.co/inclusionAI/Ling-3.0-flash-GGUF:Q4_K_M
Memory to fine-tune
Batch 1, 2,048-token sequences, gradient checkpointing; LoRA and QLoRA train rank-16 adapters on the attention projections.
Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-06. How it’s estimated
Cited scores
From third-party leaderboards, not measured by usThis model isn’t on any leaderboard we cite yet.
News
All news →- Oct 15, 2026Pricing Ant Group raises Ling-3.1-flash and Ling-3.0-flash prices Ling-3.1-flash on Ant Ling API (CNY): input ¥0.00 → ¥0.50, output ¥0.00 → ¥1.50, cache read ¥0.00 → ¥0.125 per 1M tokens. Ling-3.0-flash on Ant Ling API (CNY): input ¥0.125 → ¥0.14, output ¥0.375 → ¥0.42, cache read ¥0.025 → ¥0.028 per 1M tokens.
Price history
Ant Ling API, China · standard rate · as listedInput per 1M tokens
| From | Price |
|---|---|
| Oct 15, 2026 | ¥0.14 |
| Oct 28, 2026 | ¥0.50 |
Output per 1M tokens
| From | Price |
|---|---|
| Oct 15, 2026 | ¥0.42 |
| Oct 28, 2026 | ¥1.50 |
Changes
All changes →- Cache read price raised 12% ¥0.025 → ¥0.028 / 1M tokens · Ant Ling API, China
- Output price raised 12% ¥0.375 → ¥0.42 / 1M tokens · Ant Ling API, China
- Input price raised 12% ¥0.125 → ¥0.14 / 1M tokens · Ant Ling API, China
Sources
- Ant Ling: model pricing (opens in a new tab) developer.ant-ling.com · checked Nov 4, 2026
- Ant Ling: FAQ (opens in a new tab) developer.ant-ling.com · checked Nov 2, 2026
- Ling (opens in a new tab) developer.ant-ling.com · checked Nov 1, 2026
- Changelog (opens in a new tab) developer.ant-ling.com · checked Nov 1, 2026
- inclusionAI/Ling-3.0-flash model card (opens in a new tab) huggingface.co · checked Nov 1, 2026
- Ling (opens in a new tab) developer.ant-ling.com · checked Nov 4, 2026
- inclusionAI/Ling-3.0-flash model card (opens in a new tab) huggingface.co · checked Oct 30, 2026
- models.dev: inclusionai/ling-3.0-flash (community data, MIT) (opens in a new tab) github.com · checked Oct 15, 2026
- inclusionAI/Ling-3.0-flash model card (opens in a new tab) huggingface.co · checked Oct 30, 2026
- inclusionAI/Ling-3.0-flash config.json (opens in a new tab) huggingface.co · checked Oct 30, 2026
- inclusionAI/Ling-3.0-flash files (opens in a new tab) huggingface.co · checked Oct 30, 2026
- inclusionAI/Ling-3.0-flash-fp8 files (opens in a new tab) huggingface.co · checked Nov 5, 2026
- inclusionAI/Ling-3.0-flash-GGUF files (opens in a new tab) huggingface.co · checked Nov 4, 2026
- inclusionAI/Ling-3.0-flash-int4 files (opens in a new tab) huggingface.co · checked Oct 31, 2026
- inclusionAI/Ling-3.0-flash README.md (opens in a new tab) huggingface.co · checked Nov 4, 2026
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
Ant Group · China · developer.ant-ling.com
Related models
Snapshots, the same family and other models from this provider