Ling 3.0 Tiny
inclusionAIReleased Aug 5, 2026Open weights · MITling-3.0-tiny
- Reasoning
- yes
- Context
- 131K tokens
- Input
- text
- API features
- tools, structured outputs, JSON mode, seed, logprobs
Read Nov 6, 09:05 UTC from the hosts' published offers and OpenRouter, spec sheet from inclusionAI
Its only host, Ant Digital, serves fp8 weights (maker: bf16). Weights and context per host
| Provider | Input | Output | Cache ↑ | tok/s | First token | Uptime 24h | Checked |
|---|---|---|---|---|---|---|---|
| Ant Digitalfp8 (bf16) · 256K ctx | $0.015 | $0.045 | $0.003 | 79 | 1.39 s | 100% | Nov 6 |
1 provider · prices per million tokens, read Nov 6, 09:05 UTC · speed: OpenRouter, median of the last 30 min, read Nov 6, 09:05 UTC · uptime: OpenRouter, last 24 h · under each host: weights precision, context and max output as served, the maker's value in brackets when the host's differs
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| Ant Digital | fp8 | 256K | not read: host terms | yes | yes | yes |
Weights, context, max output: from the host where its terms allow, else as declared to OpenRouter (hover for source and date) · features as declared to OpenRouter, not verified by us
Ling 3.0 Tiny spec sheet, field by field, with sources
Ling 3.0 Tiny spec sheetmaker-declared
What inclusionAI declares, from its own weights and docs. What each host serves is in the offers: both can be true.
- Context window
- 131,072 tokens
- Parameters
- 7,893,392,800≈ 7.9B
- Active experts
- 8 of 128 active per token
- Weight precision
- bfloat16
- License
- MIT — open weights, permissiveScope: the license of the published weights only — not the maker's acceptable-use policy, nor the terms of the host you call.
- Knowledge cutoff
- not published by the maker
- Modalities
- text
- Max output (official)
- not published by the maker
- Release date
- not published by the maker
- Maker lifecycle status
- not published by the maker
Also declared in the weights
- Architecture class
- BailingMoeV3ForCausalLM
- Layers
- 24
- Vocabulary
- 157,184 tokens
- Weights first published
- August 10, 2026
- Weights last updated
- September 24, 2026
inclusionAI/Ling-3.0-tiny · config.json @ 9a98e35 · read 2026-11-06 · 6 of 10 fields published by the maker
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| Ant Digital | $0.04 | $0.14 | $0.11 |
What each host bills for 1,000 requests of a representative job
Your own workload
- Parameters
- 7.9B
- 1.3B active per token (MoE)
- Memory needed
- 5 GB
- in INT4 · 10 GB in INT8
- Smallest cloud setup
- RTX 3090
- 24 GB · $0.18/h, about $131 a month
- Worth it above
- 2B tokens
- a month, against the cheapest API at $0.06 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 5 GB | RTX 3090 · $0.18/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 10 GB | RTX 3090 · $0.18/h | near-lossless |
| FP16 (full) | 19 GB | RTX 3090 · $0.18/h | reference quality |
At home: in INT4 it fits the Intel Arc Pro B60 (24 GB) + host PC — about $1,666 once (host PC included), or $0.0634/h over 3 years, electricity aside, at 456 GB/s of memory bandwidth — that, not FLOPS, sets tokens per second; it pays for itself after about 28B tokens against the cheapest API.
Memory ≈ parameters × bytes × 1.2 · cloud: on-demand, 24/7 · builds: GGUF, AWQ, MLX, GPTQ, Ollama · break-even calculator
Other inclusionAI models · all its models, hosts and history ›
- Ling 3.0 Flash2 providers · from $0.24
- Ling 3.0 Flash VL (inclusionAI)2 providers · from $0.24
- Ling 3.1 Flash2 providers · from $0.60
- Ling 3.0 Flash Fin (inclusionAI)1 provider · from $0.29
- Ling 3.0 Flash Sante (inclusionAI)1 provider · from $0.29