Alex Getmanvarhaiset tekoälysignaalit
FI

Qwen3.8

Alibaba

Raporttien mukaanJulkaisupäivä tuntematonPäivitetty

Aikajana

  1. · Lähdelinkit · GitHub search · Alibaba · commits · onprem-ai/deployment-catalog · @tomas-polach
  2. · Lähdelinkit · GitHub search · Alibaba · commits · finereli/pyramid-mcp · @finereli
  3. · Lähdelinkit · GitHub search · Alibaba · commits · fdietze/pi-infinite-context · @fdietze
  4. · Alexin julkaisut · malliperhe · GitHub search · Alibaba · commits · agentgateway/agentgateway · @github-actions[bot]
    Ote
    json.providers.nebius.models["Qwen/Qwen3.8-27B"].name = "Qwen3.8 27B";
  5. · Lähdelinkit · GitHub search · Alibaba · commits · aabhay007/Personal-AI-Core · @aabhay007
  6. · Lähdelinkit · GitHub search · Alibaba · commits · QuantumKuba/Diffactly · @QuantumKuba
  7. · Lähdelinkit · GitHub search · Alibaba · commits · Hallo-ich-bin-PeppaPig/Singularity · @Hallo-ich-bin-PeppaPig
  8. · Lähdelinkit · GitHub search · Alibaba · commits · Azure/azureml-assets · @hanbitmyths
    Ote
    Add MAI, Qwen3.8 and Nemotron 3.5 Foundry Local coding models (#5452)
  9. · Alexin julkaisut · malliperhe · GitHub search · Alibaba · pulls · xadupre/devdash-agents · @xadupre
    Ote
    - Real Qwen3.8 27B on H200-101, physical CUDA 7: streaming generation and a follow-up turn succeeded. Used a temporary configuration with 16 KV blocks and
  10. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] qwen38_flash package entry: register() and READMEs
  11. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] MTP draft model
  12. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] KV offload pool regions
  13. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] Runner input adapter
  14. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] Hyper-connection layers
  15. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] GDN layer input preparation
  16. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] Pooled KV cache materialization
  17. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] PD transfer: identity, manifest and Raiden connector
  18. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] Config hook, geometry checks and pooled cache layout
  19. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] PLE feature: tables, host lookup, storage, offload and pooled PLE
  20. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] Sequence-parallel prefill backbone
  21. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] QSA attention layer
  22. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] Model-owned GDN op and layer (no register_oot)
  23. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] Per-group Mamba index accessors
  24. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] Mamba tail fold: export prefill checkpoints from inside the step
  25. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] In-place rows update op
  26. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] PLE Torch-to-JAX ops
  27. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] QSA Torch-to-JAX ops
  28. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] Torch bridge for the QSA kernels
  29. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] GDN input preparation kernel
  30. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] Unified KV pool kernels
  31. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] PLE lookup and gate kernels
  32. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] Hyper-connection kernels
  33. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] Pooled QSA kernel over the unified KV pool
  34. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] QSA KV write kernels (fused, main, compressed)
  35. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] QSA union-walk kernels (plan, dense, SparseCore gather, prefill)
  36. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] Qwen3.8-Flash model and registration hooks
  37. · Lähdelinkit · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Ote
    [Model][Qwen3.8] QSA main-KV decode context parallelism over rank pairs (DCP-2) kernels
  38. · Lähdelinkit · GitHub search · Alibaba · pulls · vjmichael/Lu-AI-GUI · @vjmichael
    Ote
    - Physical interactive owner Windows/Radeon Qwen3.8, Vulkan VRAM/TFFB TTFT p50/p95, and actual local installed MMProj; hosted CPU small models do not substitute.
  39. · Lähdelinkit · GitHub search · Alibaba · pulls · vitessio/vitess · @jdoupe
  40. · Lähdelinkit · GitHub search · Alibaba · pulls · nearai/cvm-compose-files · @PierreLeGuen
  41. · Lähdelinkit · GitHub search · Alibaba · pulls · michsindlinger/specwright · @michsindlinger
  42. · Alexin julkaisut · malliperhe · GitHub search · Alibaba · pulls · SceneWorks/SceneWorks · @michaeltrefry
    Ote
    SW-7119: Qwen3.8 27B describer model and tier in core, worker, API and catalog
  43. · Alexin julkaisut · malliperhe · GitHub search · Alibaba · pulls · NVIDIA/hyperflare-inference · @Raydius
    Ote
    The pinned Qwen3.8 Flash Next checkpoint trains a 262,144-token context (theta 10M, interleaved MRoPE 11/11/10). This adds a declared serving variant of the same weights
  44. · Lähdelinkit · GitHub search · Alibaba · pulls · FlashML-org/FreeToken · @zihaomu
  45. · Alexin julkaisut · malliperhe · GitHub search · Alibaba · pulls · BuQQzz/SHIELD2.0 · @BuQQzz
    Ote
    Makes Qwen3.8 27B (IQ1_M) a working coding model on an 8 GB card (RTX 2070 SUPER) through SHIELD's own llama-server.
  46. · Lähdelinkit · GitHub search · Alibaba · pulls · Azure/azureml-assets · @hanbitmyths
    Ote
    Add MAI, Qwen3.8 and Nemotron 3.5 Foundry Local coding models
  47. · Lähdelinkit · GitHub search · Alibaba · pulls · 0xburden/modelship · @0xburden
    Ote
    - Reviewed immutable catalog of 25 standalone Qwen3.8 GGUF quantizations; wizard displays sizes, numeric/letter/full-value selection and a visible UD-Q4_K_M default. No hardware-driven quant substitution; flags
  48. · Lähdelinkit · GitHub · QwenLM/qwen-code · PR
    Ote
    - The Standard preset has the same qwen3.8 effort and GLM thinking gaps and will be aligned in a follow-up
  49. · Alexin julkaisut · malliperhe · Alex Getman
    Ote
    🚨 Qwen3.8 Omni Flash is out It can see, hear and understand video, then actually act on it Give it hours of footage and it can find the right moments, translate, edit or turn it into notes. Give it a meeting and it can pull out tasks and start working on them 1M context, API from $0.43
  50. · Alexin julkaisut · malliperhe · Alex Getman
    Ote
    🚨 QWEN3.8 FLASH NEXT IS OUT The leaked specs were real: • 125B multimodal MoE • Only 6B active • 262K native context, up to 1M Qwen says it beats Claude Opus 4.6 across coding, agentic tasks, tool use and several multimodal benchmarks.
  51. · Alexin julkaisut · malliperhe · Alex Getman
    Ote
    🚨 QWEN3.8 FLASH NEXT DROPS TODAY A ModelScope description that was quickly taken down reportedly revealed: • 125B main parameters • 51B N gram embeddings • Only 6B active per token • Multimodal MoE architecture The model is also an official preview of the upcoming Qwen4 architecture.
  52. · Alexin julkaisut · Alex Getman
    Ote
    ⚡️ Qwen 3.8 27B beat GPT 5.6 Terra This happened in the AA Agentic Index, a benchmark that tests how well models handle agentic tasks. And you can run Qwen 3.8 27B locally on a single RTX 3090.
  53. · Alexin julkaisut · Alex Getman
    Ote
    ⚡️ Alibaba released Qwen3.8’s weights A model at Claude Opus 4.6 level, a flagship just six months ago, can now run on a single RTX 4090. Qwen3.8 27B uses around 17 GB of VRAM when quantized and should deliver ~50 tok/s.
  54. · Alexin julkaisut · Alex Getman
    Ote
    Alibaba just teased Qwen3.8 with 2.4T parameters This is the new Qwen flagship, with open weights coming soon. Alibaba ranks it right below Claude Fable 5. Public benchmarks are still missing, so nobody really knows how close it actually is to Fable, or how it stacks up against GPT-5.6 Sol and Kimi K3. Pricing is the fun part. Kimi K3 costs $3/$15, so Qwen3.8 will probably land in the same range. The preview is already live in Qoder. It uses 10x fewer credits during the day and 50x fewer at night, so you can basically test it for free.
Tekniset tiedot

Tutka · Qwen3.8 · Julkaisupäivä tuntematon

Kysymyksiä

Milloin Qwen3.8 julkaistiin?

Julkaisupäivä tuntematon