whittleOrg/Whittle-Next-27B-A3B
text-generation model by whittleOrg
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
The successor to Whittle-Next-26B-A3B: the same Qwen3.8-Flash-Next-format (qwen4exp) body built from Qwen3.6-35B-A3B, a 2B-row hashed n-gram memory, hyper-connection streams that are genuinely different from each other, and a distillation lineage from Qwen3.8-27B. Four phases got it here. v1–v3 (3–4 Sep) built the body, made the memory load-bearing and distilled reasoning to completion. v4 (7–10 Sep) replaced the memory's contents with an exact transfer of Qwen3.8-Flash-Next's own n-gram table, taught the layers after the injection point to read it, and then ran three nights of expert-only distillation on complete thinking traces, which took the long-reply runaways on the thinking probe from 6 in 40 to 0. v4.4 (17–18 Sep, the weights at the root of this repo) unlocked every trainable part at once and distilled it on 1,840 complete maths and code-review thinking traces; it is measurably closer to the teacher (see Measured). Runs on stock llama.cpp, no patches. Research preview,…
Read the full model card ↗ · Preview checked 2026-11-19T10:06:45.041Z
Inside the original model card — Document outline
- Whittle-Next-27B-A3B
- Status
- Which weights are which
- Measured
- v3: the last full 200-question eval
- v4.4 (the root weights) against v4.3 (reader7), same machine, same scripts
- Where the other measurements are
- How it was built
- v1 — the 27B body: table doubled, hyper-connections unlocked (3 Sep)
- v2 — the memory pulls weight (3 Sep)
- v3 — reasoning distill to completion (4 Sep)
- v4 — the memory becomes Qwen's memory, the experts learn from thinking traces (7–10 Sep)
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
whittleOrg/Whittle-Next-27B-A3B is a text-generation model repository published by whittleOrg on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-generation
- Library
- transformers
- Recent downloads (30 days)
- 1,301
- Cumulative likes
- 70
- Hugging Face trending score
- 38
- Reported safetensors parameters
- 27,568,288,915
- Architecture
- Qwen4ExpForCausalLM
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-03T09:54:43.000Z
- Last modified
- 2026-10-14T05:47:59.000Z
Compatibility and lineage
Reported languages: en, zh, multilingual
Reported base models: Qwen/Qwen3.6-35B-A3B, logic65/Whittle-Next-26B-A3B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-19T07:00:11.321Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.