Alex Getmanwczesne sygnały AI
PL

Qwen3.8

Alibaba

Według doniesieńData premiery nieznanaZaktualizowano

Oś czasu

  1. · Odnośniki źródłowe · GitHub search · Alibaba · commits · onprem-ai/deployment-catalog · @tomas-polach
  2. · Odnośniki źródłowe · GitHub search · Alibaba · commits · finereli/pyramid-mcp · @finereli
  3. · Odnośniki źródłowe · GitHub search · Alibaba · commits · fdietze/pi-infinite-context · @fdietze
  4. · Wpisy Alexa · rodzina modeli · GitHub search · Alibaba · commits · agentgateway/agentgateway · @github-actions[bot]
    Fragment
    json.providers.nebius.models["Qwen/Qwen3.8-27B"].name = "Qwen3.8 27B";
  5. · Odnośniki źródłowe · GitHub search · Alibaba · commits · aabhay007/Personal-AI-Core · @aabhay007
  6. · Odnośniki źródłowe · GitHub search · Alibaba · commits · QuantumKuba/Diffactly · @QuantumKuba
  7. · Odnośniki źródłowe · GitHub search · Alibaba · commits · Hallo-ich-bin-PeppaPig/Singularity · @Hallo-ich-bin-PeppaPig
  8. · Odnośniki źródłowe · GitHub search · Alibaba · commits · Azure/azureml-assets · @hanbitmyths
    Fragment
    Add MAI, Qwen3.8 and Nemotron 3.5 Foundry Local coding models (#5452)
  9. · Wpisy Alexa · rodzina modeli · GitHub search · Alibaba · pulls · xadupre/devdash-agents · @xadupre
    Fragment
    - 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. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] qwen38_flash package entry: register() and READMEs
  11. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] MTP draft model
  12. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] KV offload pool regions
  13. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] Runner input adapter
  14. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] Hyper-connection layers
  15. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] GDN layer input preparation
  16. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] Pooled KV cache materialization
  17. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] PD transfer: identity, manifest and Raiden connector
  18. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] Config hook, geometry checks and pooled cache layout
  19. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] PLE feature: tables, host lookup, storage, offload and pooled PLE
  20. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] Sequence-parallel prefill backbone
  21. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] QSA attention layer
  22. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] Model-owned GDN op and layer (no register_oot)
  23. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] Per-group Mamba index accessors
  24. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] Mamba tail fold: export prefill checkpoints from inside the step
  25. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] In-place rows update op
  26. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] PLE Torch-to-JAX ops
  27. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] QSA Torch-to-JAX ops
  28. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] Torch bridge for the QSA kernels
  29. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] GDN input preparation kernel
  30. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] Unified KV pool kernels
  31. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] PLE lookup and gate kernels
  32. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] Hyper-connection kernels
  33. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] Pooled QSA kernel over the unified KV pool
  34. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] QSA KV write kernels (fused, main, compressed)
  35. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] QSA union-walk kernels (plan, dense, SparseCore gather, prefill)
  36. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] Qwen3.8-Flash model and registration hooks
  37. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
    Fragment
    [Model][Qwen3.8] QSA main-KV decode context parallelism over rank pairs (DCP-2) kernels
  38. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vjmichael/Lu-AI-GUI · @vjmichael
    Fragment
    - 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. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · vitessio/vitess · @jdoupe
  40. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · nearai/cvm-compose-files · @PierreLeGuen
  41. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · michsindlinger/specwright · @michsindlinger
  42. · Wpisy Alexa · rodzina modeli · GitHub search · Alibaba · pulls · SceneWorks/SceneWorks · @michaeltrefry
    Fragment
    SW-7119: Qwen3.8 27B describer model and tier in core, worker, API and catalog
  43. · Wpisy Alexa · rodzina modeli · GitHub search · Alibaba · pulls · NVIDIA/hyperflare-inference · @Raydius
    Fragment
    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. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · FlashML-org/FreeToken · @zihaomu
  45. · Wpisy Alexa · rodzina modeli · GitHub search · Alibaba · pulls · BuQQzz/SHIELD2.0 · @BuQQzz
    Fragment
    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. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · Azure/azureml-assets · @hanbitmyths
    Fragment
    Add MAI, Qwen3.8 and Nemotron 3.5 Foundry Local coding models
  47. · Odnośniki źródłowe · GitHub search · Alibaba · pulls · 0xburden/modelship · @0xburden
    Fragment
    - 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. · Odnośniki źródłowe · GitHub · QwenLM/qwen-code · PR
    Fragment
    - The Standard preset has the same qwen3.8 effort and GLM thinking gaps and will be aligned in a follow-up
  49. · Wpisy Alexa · rodzina modeli · Alex Getman
    Fragment
    🚨 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. · Wpisy Alexa · rodzina modeli · Alex Getman
    Fragment
    🚨 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. · Wpisy Alexa · rodzina modeli · Alex Getman
    Fragment
    🚨 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. · Wpisy Alexa · Alex Getman
    Fragment
    ⚡️ 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. · Wpisy Alexa · Alex Getman
    Fragment
    ⚡️ 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. · Wpisy Alexa · Alex Getman
    Fragment
    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.
Dane techniczne

Radar · Qwen3.8 · Data premiery nieznana

Pytania

Kiedy wydano Qwen3.8?

Data premiery nieznana