Ling-2.6-flash
inclusionAI · released Apr 28, 2026 · inclusionAI/Ling-2.6-flash-int4
- Type
- Open weightsMIT License
- Params
- 107B
- Context
- 262K
active per word not recorded by us · about 197K words of context
Our take
Written Sep 2, 2026Ling-2.6-flash is a 107.3-billion-parameter text-only model from inclusionAI with a permissive MIT licence and a 262,144-token request limit. Its hosted rate is the cheapest in its small offer set, making it a budget pick for coding and long-context text work where licensing flexibility matters.
Pick this for budget text generation with a permissive licence — MIT allows commercial use and redistribution without attribution. Use it for coding tasks, where it scores 66 points above its own overall mark, or for long-context work up to 262K tokens. Skip it if creative writing quality matters, or if you need measured throughput at the cheapest price point.
The case for it
- Permissive MIT licence with no attribution or copyleft requirements.
- Cheapest hosted tier in its own three-offer set.
- Coding performance leads its own benchmark profile by 66.4 points.
The case against it
- Creative writing is its weakest measured area, 76.5 points below its overall score and 143 below its coding mark.
- No measured throughput at the cheapest price point; speed and cost are split across separate tiers.
- Dense 107.3 billion parameters with no disclosed efficiency architecture.
How good is it?
An open text model for chat and drafting, though it trails most models on everyday questions and prose.
- getting answers to everyday questionsArena Text (overall) · 127th of 168
- drafts, rewrites and editingArena Creative Writing · 144th of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)127th of 168 · 1344
CodingWriting and fixing code on its own
Arena Coding120th of 168 · 1410
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing144th of 168 · 1267
Arena Creative Writing is the only board that has scored it for this.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done.
Every published score for this model6 scoresEvery figure we hold, from 6 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M2 Max (38-core GPU) · 96 GB
Borderline fit on an estimated size. It leaves 0.1 GB spare on a size we calculated rather than measured, and a 10% error either way would change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked between 21 days and 39 days ago — each listing carries its own date.
- per 1M tokens
- $0.010 in / $0.030 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.010 / $0.030checked 39 days ago | 262K | not measured | Unknown | Unknown | Unknown |
| Novita AIDirect | $0.10 / $0.30checked 21 days ago | 262K | not measured | Unknown | Unknown | Unknown |
Novita AIAcross the 2 listings we hold: 0 say they do not train on prompts, 0 say they do and 2 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Novita AIDirect |
Tool calling: 1 of 2 listings says yes, 1 publishes no parameter list. JSON output: 1 of 2 listings says yes, 1 publishes no parameter list. Strict schema: 1 of 2 listings says yes, 1 publishes no parameter list.
Models people weigh against Ling-2.6-flash
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- 1 of 2 listings publishes no parameter list, so what its API accepts is unknown to us.
- We do not hold the active parameter count for it, so how much of it runs on any one token is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 2 listings do not say whether they train on prompts.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsMIT License, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
MIT License
Fully permissive: do anything with attribution. No patent grant, unlike Apache-2.0.
Identifiers
- Hugging Face
- inclusionAI/Ling-2.6-flash-int4
- Architecture
- Mixture of experts
- Takes in, gives back
- Text in, text out
- Catalogue slug
- inclusionai-ling-2-6-flash