Qwen3.8 27B OBLITERATED
27.8B parameters · 256k context · Apache 2.0 · released 2026-08-19
chatcodingagenticreasoning
What to run it on in the US
Fully in memory at 64k context, priced at retailers today.
Nothing we price holds this model fully in memory.
All hardware that runs it
Everything we price, best value first. Two cards split the model by layers.
Nothing we price can run it at this context.
Memory needed
Weights, KV cache and runtime buffers at each context length (KV cache at fp16).
| Quant | File |
|---|
Run it
Copy a command for the runtime you use.
No published builds to run yet.
Notes
Abliterated (safety guardrails removed) model; card recommends greedy decoding with repetition_penalty 1.15 and no system prompt. MMLU is 82.3% vs 84.5% for stock; MLX support is pending.
Questions
- What licence is Qwen3.8 27B OBLITERATED released under?
- Apache 2.0, which allows commercial use.