AI Model Timeline

Tracking the accelerating release frequency of frontier AI models.

Qwen3.8-Flash-Next

Alibaba·

LLMsopen-weightMulti-GPU Self-Host

Overview

Open-weight multimodal MoE that Qwen ships as an early preview of the architecture behind Qwen4 — the same role Qwen3-Next played for Qwen3.5. A 125B main model plus a separate 51B N-gram embedding table, with 6B parameters activated per token. Four changes carry the release: a GDN + QSA hybrid attention stack (Gated DeltaNet compresses the history, Qwen Sparse Attention picks important context at micro-block granularity), a Gated Residual stream widened to four dynamically gated branches, the N-gram embedding table itself (looked up from local context, offloadable to host memory with asynchronous prefetching), and a Muon optimizer with a scaling law refitted for the new architecture. Native context is 262,144 tokens. Qwen reports roughly 1/9 the training cost of Qwen3.7-Plus. Because only 6B parameters are active and the embedding table can sit in system RAM, Unsloth's smallest quant runs on a 78 GB RAM / unified-memory machine without a discrete GPU. A production Qwen3.8-Flash for the QwenCloud API was announced at $0.16 / $0.47 per MTok but is not live yet, so no cloud entry is tracked; the license file ships with the weights and is not stated in the GitHub release.

Capabilities and innovations

125B main + 51B N-gram embedding parameters, 6B active per token262K native contextNatively multimodal (text and vision)GDN + QSA hybrid attentionN-gram embedding table offloadable to host RAMRuns from system RAM without a discrete GPU (78 GB smallest quant)Early open release of the Qwen4 architectureQwen Sparse Attention (QSA) with micro-block context selectionGated Residual: 4-branch residual stream with dynamic gatingN-gram Embedding with asynchronous host-memory prefetchingMuon optimizer with refitted scaling law

Benchmarks

BenchmarkScoreSource
GPQA Diamond91.7%vendor
GPQA Diamond 91.7 from Qwen's launch table. The blog and the Hugging Face model card are both unreachable from this environment (egress-blocked); the value was taken from consistent secondary transcriptions of the table and not independently reproduced. Same caveat as the Qwen3.8-27B entry.
Humanity’s Last Exam (no tools)35.9%vendor
HLE 35.9 from the same launch table. Caveat beyond the transcription one: Qwen states this run is graded by GPT-4o rather than the benchmark's default grader, so it is not strictly comparable to the HLE values stored for other models. Same transcription caveat as GPQA.
SWE-bench Pro62.5%vendor
SWE-bench Pro 62.5 from the same launch table (Qwen3.8-27B: 61.7, Qwen3.7-Plus: 55.8). Same transcription caveat as GPQA.
  • Terminal-Bench 2.x: not reported by the vendor — Qwen's launch table leans on its own agentic suite (DeepSWE 1.1 58.7, SWE-bench Multilingual 81.0, LiveCodeBench v6 91.9, JobBench 55.7) and publishes no Terminal-Bench figure. Neither Artificial Analysis nor Vals AI lists the model as of 2026-08-26.
  • MMLU-Pro: not reported by the vendor — MMLU-Pro is only mentioned for the base model, as one of the 8 of 14 benchmarks Qwen3.8-Flash-Next-Base is said to lead; no number was published for the instruct model.
  • MMMU-Pro: independent evaluation pending — The model is natively multimodal, but no MMMU-Pro figure appears in the launch table and no independent run is available yet.
  • SWE-bench Verified: not reported by the vendor — Era-1 benchmark; Qwen reports SWE-bench Pro and its own coding suite instead.
  • Terminal-Bench 3.0: not reported by the vendor

Architecture and hardware

Parameters
176B total, 6B active per token (MoE)
Estimated VRAM at Q4
~102 GB, Multi-GPU Self-Host class
Quantization formats
GGUF, FP8, NVFP4, BF16
Recommended runtime
llama.cpp
License
Open (final license pending)

Links

More from Alibaba

Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.