Open weights and the routing market

Open-weight models are taking production routing share faster than their licences are settling.

28 entries · Aug 26, 2026 to Sep 15, 2026 · 16 editions

  1. Aug 26, 2026

    Developers are routing production traffic to an anonymous provider that retains their prompts

    Ox Alpha took 23.2 trillion OpenRouter tokens this week, first place by more than double the next model. Joseph W. Elstner, August 23, matched its tokenizer to Zhipu's released GLM-5 vocabulary across 95 probes at zero error, but cautioned this “establishes vocabulary identity, not ownership.” OpenRouter states the provider retains prompts and completions. Elstner
  2. Aug 26, 2026

    WATCHQwen open-sources Qwen3.8-Flash-Next tonight

    a multimodal mixture-of-experts model previewing the Qwen4 architecture, with an FP8 variant. No specs and no benchmarks disclosed yet. TechNode
  3. Aug 27, 2026

    Open weights are winning the routing market before they even have a name

    Z.ai confirmed August 26 that Ox Alpha, first on OpenRouter by routed tokens, was GLM-5.3-Flash, then released the weights under MIT: 320B total, 18B active. Simon Willison ran Qwen3.8-Flash-Next on a DGX Spark the day it shipped, 125B total but “only 6B active”. Daniel Han had Unsloth GGUFs ready day zero. The identity question filed here Monday moved, and it moved open. Willison
  4. Aug 27, 2026

    SHIPZ.ai opens GLM-5.3-Flash under MIT

    320B total, 18B active, 1M context, multimodal. This is the model that ran anonymously as Ox Alpha, served on Chinese AI chips. Z.ai
  5. Aug 27, 2026

    Deep Cogito raised a $43M Series A to build open-weight models companies control themselves. WSJ
  6. Aug 28, 2026

    SHIPUnsloth v0.1.804-beta quantizes GLM-5.3-Flash and Qwen3.8-Flash-Next

    GLM-5.3 fits 102GB of RAM plus VRAM, Qwen3.8 fits 75GB. It also fixes NVIDIA freezes under Wayland and AMD model-load crashes. Release
  7. Aug 30, 2026

    SHIPZ.ai puts full GLM-5.3 under a custom license

    Companies above $10B revenue over any 12 months must pass Z.ai's security review before commercial use. GLM-5.2 was MIT, and Flash stays MIT. The New Stack
  8. Aug 30, 2026

    SHIPTencent opens Hy4 preview at 770B total, 49B active

    1M context and 1.56TB of weights, with a chat template carrying two reasoning modes: high by default, no_think to switch off. Willison ran it August 29. Willison
  9. Sep 1, 2026

    SHIPDeepSeek open-sources its first multimodal model

    V4-Flash-Vision-Exp shipped on Hugging Face under an MIT license August 31, ten days after the same weights went live on DeepSeek's API. DeepSeek says it beats the text-only V4-Flash on chart-reading and agentic benchmarks; the company calls its own eval set narrow. Hugging Face
  10. Sep 1, 2026

    ACTGLM-5.3-Flash still has no merged llama.cpp support

    Three competing pull requests have sat open since August 26; the author of one flags that numerical validation against the original weights was never finished. Unsloth's own fork branch is the only working local path for now. llama.cpp
  11. Sep 1, 2026

    vLLM v0.28.0 shipped August 26 with Kimi K3 decode-context-parallel optimizations, 584 commits from 270 contributors. vLLM
  12. Sep 2, 2026

    Open-weight adoption is outrunning the tooling that runs it locally

    GLM-5.3-Flash led OpenRouter's token volume at roughly 1.5 trillion tokens a day as of August 30, ahead of DeepSeek V4 Flash, while llama.cpp mainline still cannot load it. Three pull requests remain unmerged; Daniel Han's fork hit a new Metal integer-overflow bug September 1. A separate opencode issue found the model's reasoning collapsing into repeated exclamation marks under SGLang's tool-calling parser. OpenRouter · Han · opencode
  13. Sep 2, 2026

    WATCHZ.ai's H1 revenue jumps almost 400% but misses estimates

    Revenue hit 954 million yuan, about $142 million, with API and open-platform business now 86.5% of the total. Net loss narrowed 12% to 2.07 billion yuan, against the backdrop of GLM-5.3's new revenue-gated license. SCMP
  14. Sep 3, 2026

    WATCHllama.cpp merges the Metal fix for the GLM-5.3-Flash overflow bug

    PR #28210, merged September 2, promotes offset math to 64-bit and ends the long-context collapse Daniel Han flagged September 1. Three separate pull requests adding GLM-5.3-Flash support to llama.cpp mainline remain open. llama.cpp
  15. Sep 4, 2026

    GLM-5.3-Flash's OpenRouter volume rose to 1.9 trillion tokens a day; mainline llama.cpp support is still unmerged. OpenRouter
  16. Sep 5, 2026

    Enterprises are moving production workloads to open-weight models once they're good enough, not waiting for frontier quality

    Gergely Orosz's September 3 Pulse newsletter reports companies shifting less-complex workloads to open models for roughly 50% lower infrastructure costs. The New York Times framed the same shift September 4 as a "good enough" threat to Anthropic and OpenAI's premium pricing, the same week Fable 5.1 itself got a 75% cache-read price cut. Orosz
  17. Sep 6, 2026

    WATCHvLLM's GLM-5.3 ROCm accuracy fix approved, not yet merged

    The fix for vLLM's model-runner bug that collapsed GLM-5.3 accuracy on ROCm from 91.6 percent to 14.9 percent won reviewer approval September 2, closing in on landing; the VLLM_USE_V2_MODEL_RUNNER=1 workaround still applies until it merges. vLLM PR #54925
  18. Sep 6, 2026

    Three competing llama.cpp pull requests for GLM-5.3-Flash support remain unmerged; reviewers flag a 7 percent decode-throughput cost in one. llama.cpp PR #27754
  19. Sep 7, 2026

    Support for GLM-5.3-Flash in llama.cpp is consolidating around one implementation, not the one its most prominent contributor wrote

    Three competing llama.cpp pull requests for GLM-5.3-Flash have been open since late August; reviewers are now converging on PR #27773 over Daniel Han's #27754, which still repeats tokens at deep context. Han pushed back: 'I know there is another impl, but this impl has been validated and utilized by many folks and works fine.' A third PR, #27752, is being abandoned in #27773's favor. llama.cpp PR #27773 · llama.cpp PR #27754
  20. Sep 7, 2026

    Unsloth's v0.1.806-beta doubled decode speed for GLM-5.3-Flash and Qwen3.8-Flash-Next via multi-token prediction, now on by default. Unsloth
  21. Sep 7, 2026

    OpenRouter rankings still show no reversal: DeepSeek V4 Flash leads GLM-5.3-Flash, 1.7 trillion tokens a day versus 1.5 trillion. OpenRouter
  22. Sep 9, 2026

    The production routing leaderboard for open-weight models reshuffled again this week, and the new leader is a model most readers haven't heard of yet

    OpenRouter's rankings as of September 8 put Tencent's Hy4 Preview, released August 28, at 3.4 trillion tokens a day, more than any other model tracked, while GLM-5.3-Flash (1.8T) overtook DeepSeek V4 Flash (1.7T), a reversal from earlier in the week. Teortaxes, testing Hy4 directly, called it 'outside my expectations.' vLLM shipped support for both models on release day, September 9. OpenRouter · Teortaxes
  23. Sep 9, 2026

    SHIPvLLM 0.29.0 makes Model Runner V2 the default and adds day-one support for Hy4 and Qwen3.8-Flash-Next

    The September 9 release, 594 commits from 277 contributors, turns on FlashInfer all-reduce by default, drops ten deprecated model architectures, and replaces the old module-based server invocation with vllm serve. vLLM v0.29.0
  24. Sep 9, 2026

    Nathan Lambert: Chinese open-model releases increasingly attach revenue thresholds and security reviews, while Western labs still default to Apache 2.0. Lambert
  25. Sep 10, 2026

    llama.cpp's three competing GLM-5.3-Flash pull requests remain unmerged; Daniel Han's PR #27754 still needs two maintainer approvals. llama.cpp PR #27754
  26. Sep 11, 2026

    Tencent's Hy4 Preview keeps its OpenRouter lead; OpenAI's GPT-5.6 Luna is the fastest riser, second ahead of GLM-5.3-Flash. OpenRouter
  27. Sep 14, 2026

    The blocking CUDA crash in GLM-5.3-Flash's llama.cpp port was fixed September 11; the merge still awaits maintainer review. llama.cpp PR #27754
  28. Sep 15, 2026

    SHIPllama.cpp v0.4.1 drops mmap and mlock for one load-mode flag

    Georgi Gerganov's release adds Maple 20B-A1B and Tencent Hy4 support but removes --mmap, --mlock and --direct-io in favor of a single --load-mode flag — a breaking change for any script or config that used them. llama.cpp releases