Alex GetmanAI चे आगाऊ संकेत
MR

Qwen3.8

Alibaba

वृत्तांनुसाररिलीजची तारीख अज्ञातअद्ययावत

कालरेषा

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

रडार · Qwen3.8 · रिलीजची तारीख अज्ञात

प्रश्न

Qwen3.8 कधी रिलीज झाले?

रिलीजची तारीख अज्ञात