Qwen3.8
Alibaba
Linimasa
- · Tautan bukti · GitHub search · Alibaba · commits · onprem-ai/deployment-catalog · @tomas-polach
- · Tautan bukti · GitHub search · Alibaba · commits · finereli/pyramid-mcp · @finereli
- · Tautan bukti · GitHub search · Alibaba · commits · fdietze/pi-infinite-context · @fdietze
- · Postingan Alex · keluarga model · GitHub search · Alibaba · commits · agentgateway/agentgateway · @github-actions[bot]
Kutipan
json.providers.nebius.models["Qwen/Qwen3.8-27B"].name = "Qwen3.8 27B";
- · Tautan bukti · GitHub search · Alibaba · commits · aabhay007/Personal-AI-Core · @aabhay007
- · Tautan bukti · GitHub search · Alibaba · commits · QuantumKuba/Diffactly · @QuantumKuba
- · Tautan bukti · GitHub search · Alibaba · commits · Hallo-ich-bin-PeppaPig/Singularity · @Hallo-ich-bin-PeppaPig
- · Tautan bukti · GitHub search · Alibaba · commits · Azure/azureml-assets · @hanbitmyths
Kutipan
Add MAI, Qwen3.8 and Nemotron 3.5 Foundry Local coding models (#5452)
- · Postingan Alex · keluarga model · GitHub search · Alibaba · pulls · xadupre/devdash-agents · @xadupre
Kutipan
- 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
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] qwen38_flash package entry: register() and READMEs
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] MTP draft model
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] KV offload pool regions
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] Runner input adapter
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] Hyper-connection layers
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] GDN layer input preparation
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] Pooled KV cache materialization
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] PD transfer: identity, manifest and Raiden connector
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] Config hook, geometry checks and pooled cache layout
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] PLE feature: tables, host lookup, storage, offload and pooled PLE
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] Sequence-parallel prefill backbone
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] QSA attention layer
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] Model-owned GDN op and layer (no register_oot)
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] Per-group Mamba index accessors
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] Mamba tail fold: export prefill checkpoints from inside the step
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] In-place rows update op
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] PLE Torch-to-JAX ops
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] QSA Torch-to-JAX ops
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] Torch bridge for the QSA kernels
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] GDN input preparation kernel
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] Unified KV pool kernels
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] PLE lookup and gate kernels
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] Hyper-connection kernels
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] Pooled QSA kernel over the unified KV pool
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] QSA KV write kernels (fused, main, compressed)
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] QSA union-walk kernels (plan, dense, SparseCore gather, prefill)
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] Qwen3.8-Flash model and registration hooks
- · Tautan bukti · GitHub search · Alibaba · pulls · vllm-project/vllm-torchtpu · @DRZDONG
Kutipan
[Model][Qwen3.8] QSA main-KV decode context parallelism over rank pairs (DCP-2) kernels
- · Tautan bukti · GitHub search · Alibaba · pulls · vjmichael/Lu-AI-GUI · @vjmichael
Kutipan
- 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.
- · Tautan bukti · GitHub search · Alibaba · pulls · vitessio/vitess · @jdoupe
- · Tautan bukti · GitHub search · Alibaba · pulls · nearai/cvm-compose-files · @PierreLeGuen
- · Tautan bukti · GitHub search · Alibaba · pulls · michsindlinger/specwright · @michsindlinger
- · Postingan Alex · keluarga model · GitHub search · Alibaba · pulls · SceneWorks/SceneWorks · @michaeltrefry
Kutipan
SW-7119: Qwen3.8 27B describer model and tier in core, worker, API and catalog
- · Postingan Alex · keluarga model · GitHub search · Alibaba · pulls · NVIDIA/hyperflare-inference · @Raydius
Kutipan
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
- · Tautan bukti · GitHub search · Alibaba · pulls · FlashML-org/FreeToken · @zihaomu
- · Postingan Alex · keluarga model · GitHub search · Alibaba · pulls · BuQQzz/SHIELD2.0 · @BuQQzz
Kutipan
Makes Qwen3.8 27B (IQ1_M) a working coding model on an 8 GB card (RTX 2070 SUPER) through SHIELD's own llama-server.
- · Tautan bukti · GitHub search · Alibaba · pulls · Azure/azureml-assets · @hanbitmyths
Kutipan
Add MAI, Qwen3.8 and Nemotron 3.5 Foundry Local coding models
- · Tautan bukti · GitHub search · Alibaba · pulls · 0xburden/modelship · @0xburden
Kutipan
- 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
- · Tautan bukti · GitHub · QwenLM/qwen-code · PR
Kutipan
- The Standard preset has the same qwen3.8 effort and GLM thinking gaps and will be aligned in a follow-up
- · Postingan Alex · keluarga model · Alex Getman
Kutipan
🚨 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
- · Postingan Alex · keluarga model · Alex Getman
Kutipan
🚨 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.
- · Postingan Alex · keluarga model · Alex Getman
Kutipan
🚨 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.
- · Postingan Alex · Alex Getman
Kutipan
⚡️ 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.
- · Postingan Alex · Alex Getman
Kutipan
⚡️ 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.
- · Postingan Alex · Alex Getman
Kutipan
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.
Spesifikasi
Radar · Qwen3.8 · Tanggal rilis tidak diketahui
Pertanyaan
Kapan Qwen3.8 dirilis?
Tanggal rilis tidak diketahui