Qwen3.8-27B-DSpark-Multilingual

Qwen3.8-27B DSpark Multilingual

A multilingual finetune of the RadixArk/Qwen3.8-27B-DSpark speculative-decoding drafter for Qwen/Qwen3.8-27B.

Two checkpoints are published:

• main (this revision): the balanced checkpoint (1 epoch). Best all-rounder for agentic coding plus multilingual chat.
• epoch1-multilingual-max: the multilingual-max checkpoint (1.8 epochs). Strongest on non-English prose and reasoning, pays for it on English code and math. Load it with revision="epoch1-multilingual-max".

Measured (frozen battery v1, greedy, all three columns measured the same evening on the same DGX Spark, same load state, two-call wall-clock delta)

Read it honestly: no column dominates. Finetuning a drafter redistributes acceptance along the training mix, it does not create free speed everywhere. The stock drafter keeps the math crown. main buys +16 % on English code and +8 to +16 % on French/German prose at a 7 % math cost. The multilingual-max revision buys +15 to +25 % across non-English cells at a 7 to 12 % cost on English code and math, and loses technical French. Pick by workload; speculative decoding is lossless by construction, so output quality is identical in every case, only speed moves.

Context worth knowing: DFlash2 (z-lab) landed in SGLang main on 2026-08-19 and reports strong gains over stock DSpark on English evals. If your stack can run it, benchmark it against these checkpoints on your own workload; if you are on a pinned DSpark setup today, these are drop-in.

Why

The stock drafter was trained on Open-PerfectBlend: ~78 % English math and code, non-thinking. Acceptance collapses on everything else: free prose sits at 1.5-1.9 accepted tokens per step in any language, and thinking-mode output was never in its distribution. This finetune targets what agent users actually generate: 10 languages, free prose, thinking traces (26 % of the corpus, including xhigh), multi-turn, and tool calls.

Training

• Corpus: 18,290 conversations, prompts from license-clean sources (open-perfectblend Apache/MIT, WildChat-1M ODC-BY prompts only, oasst2 Apache, aya Apache, own prompt banks). Every response regenerated on-policy by Qwen3.8-27B itself at the official sampling settings, so the drafter learns the target's true output distribution. Benchmark prompts excluded from the corpus.
• Languages: EN 32 %, FR 27 %, DE 11 %, ES 8 %, ZH 7 %, IT/PT/JA/RU/NL the rest. Kinds: chat, replay, prose, technical, code, math, multi-turn, tool-call. 26 % thinking (incl. xhigh).
• Method: SpecForge dspark objective, warm start from the RadixArk checkpoint, LR 1e-5 (swept: higher LRs buy prose by destroying code), bf16 target activations (layers 4/16/28/40/52 + final norm), single DGX Spark (GB10). main is the epoch-1 checkpoint; the multilingual-max revision adds a further 0.8 epoch, which kept shifting acceptance toward the multilingual cells.

Serve it

Drop-in replacement for the stock drafter in any SGLang Qwen3.8 setup:

--speculative-algorithm DSPARK \
--speculative-draft-model-path hasanbasbunar/Qwen3.8-27B-DSpark-Multilingual \
--speculative-dspark-block-size 7 --speculative-draft-model-quantization unquant

Add --speculative-draft-model-revision epoch1-multilingual-max for the multilingual-max checkpoint.

Full pinned, one-command GB10 setup (config, systemd, benchmark battery): github.com/hasso5703/dgx-spark-qwen38. Speculative decoding is lossless: the target verifies every drafted token, so output quality is unchanged at any temperature.

Credits

Base drafter and method: RadixArk, DSpark paper, SpecForge. Trained and measured on one ASUS Ascent GX10 (DGX Spark, GB10).