Skip to content
Weights Not Walls
Menu

whittleOrg

Whittle-Next-27B-A3B

Unreviewed

Not reviewed: shown with only what the Hub data supports. Our rule was not met:

  • not from an organisation on our makers list
  • below the usage threshold (100000 downloads or 500 likes)

The reviewed rule

Size
27.6B parameters, 3.0B active (from the repo name)counted from the safetensors header on the Hub
Licence
unknown, Apache License 2.0Our reading, check the licence: You can use, change and redistribute the model, including commercially. Keep the licence and any notices, and say which files you changed; you do not have to publish your changes. It includes a patent licence that ends for anyone who sues over patents in the work.
On the Hub since
3 Sep 2026the date the repo was created
Context length
Not known
Fine-tune
of Qwen/Qwen3.6-35B-A3BQwen4ExpForCausalLM
On Hugging Face
whittleOrg/Whittle-Next-27B-A3B1.4k downloads in the last 30 days, 85 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

  • GSM8K exact match (v3 Q8_0 GGUF, stock llama.cpp, serving sampler), main, test86.5
  • GSM8K exact match, thinking on, 2048-token cap (v3 Q8_0 GGUF), main, test86.5
  • Whittle long-context reading harness (private repository; transcripts withheld) questions correct at 4k tokens (v4.3, Q8_0)100
  • Whittle long-context reading harness (private repository; transcripts withheld) questions correct at 8k tokens (v4.3, Q8_0)83.3
  • Whittle long-context reading harness (private repository; transcripts withheld) questions correct at 26k to 75k tokens (v4.3, Q8_0; parent Qwen3.6-35B-A3B scores 100)66.7

Values as the card gives them, unscaled. Source: the model card on the Hugging Face Hub. Claimed scores are never mixed with independent ones.

Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.

Run it yourself

no conversions read for this model

Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 2.0 GB, a rough allowance by model size, because we do not have this model's attention config. Choose a machine above to see a verdict for each format. Method

Estimated sizes no measured GGUF files for this model

From the parameter count and the bits per weight of each level (the median measured over the GGUF files in our snapshot, or the format's block size). Real files differ by a few per cent.

FormatSizeMemory neededRepo
Q4_K_M4.88 bits per weight, measured median15.7 GBestimated18.2 GB15.7 + 2.0 + 0.50
Q5_K_M5.71 bits per weight, measured median18.3 GBestimated20.8 GB18.3 + 2.0 + 0.50
Q6_K6.57 bits per weight, measured median21.1 GBestimated23.6 GB21.1 + 2.0 + 0.50
Q8_08.50 bits per weight, measured median27.3 GBestimated29.8 GB27.3 + 2.0 + 0.50

Original weights size from the safetensors header, for vLLM, SGLang, Transformers

FormatSizeMemory neededRepo
BF16original weights51.3 GBfile size53.8 GB51.3 + 2.0 + 0.50
hf download whittleOrg/Whittle-Next-27B-A3B --local-dir Whittle-Next-27B-A3B

Run it by API

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.

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.