GLM-5.3-Maya-XS, Maya's own quant of Z.ai's GLM-5.3 (744B) at 170 GB; prompts read fast with IQ1_M experts; faster GLM-5.3 decode and drafting; DeepSeek's one-GPU decode back to speed; and fixes.
- GLM-5.3-Maya-XS: Maya's own quant of Z.ai's GLM-5.3 (744B), with the routed experts in about 1.6 bits. It is 170.0 GB in 4 files and as close to the original as unsloth's UD-IQ1_S (the same mean KL divergence, 0.506, and the same top token 81.8% of the time) at 78% of its size.
- The files: peasantsmith/GLM-5.3-Maya-GGUF, pinned and checked shard by shard. Set it up with
./maya.sh --setup --model glm-5.3-maya-xs(Windows:START-MAYA.bat --setup --model glm-5.3-maya-xs), or pick it in the setup's list or on the dashboard's Models page. It is shown as "GLM-5.3 (744B) · Maya-XS". - Memory: about 176 GB of VRAM and RAM together keeps every expert in memory, so 192 GB is recommended (see docs/MEMORY.md). With less, Maya reads the rest from the SSD while it answers.
- Where it runs: NVIDIA from the Tesla V100 on and AMD (the Strix and Gorgon Halo included), Linux and Windows. Text only, like GLM-5.3 itself, with drafting from its own NextN block.
- The files: peasantsmith/GLM-5.3-Maya-GGUF, pinned and checked shard by shard. Set it up with
- Prompts read fast with IQ1_M experts: GGUFs whose experts use IQ1_M (and a few older types) used to read the whole prompt one token at a time. Now only those expert matrices take a slower path and everything else runs as before, on NVIDIA and AMD. With GLM-5.3-Maya-XS, prompts are read about 9-13x faster at 1-2K tokens and about 21x faster at 8K than in v1.1.57.
- Faster GLM-5.3 decode:
- The pack keeps the GGUF's Q8_0 attention weights as they are instead of converting them: about 8% faster decode on a Gorgon Halo, the same speed on NVIDIA. Answers can differ slightly from v1.1.57's; the next setup rebuilds an existing GLM-5.3 pack once.
- The part of the decode that runs on the CPU computes four rows at once: the same answers bit for bit, about 3-5% faster GLM-5.3-Maya-XS decode on our test PC.
- GLM-5.3 on an AMD Ryzen AI Max APU (Strix / Gorgon Halo): drafting on one GPU is now chosen by measurement: the setup's speed calibration tries decode with and without drafting on a few short chats and keeps the faster. With GLM-5.3-Maya-XS on a 192 GB Gorgon Halo it kept drafting, about 12% faster than without it, with the same answers. The start no longer shows a misleading "LOW" VRAM warning there.
- Faster, smarter drafting for GLM-5.3 and GLM-5.3-Flash: Q5_K weights now take the fast multi-token path (the same answers). On several GPUs, GLM-5.3 hands the prompt between GPUs with a quarter of the data,
"spec": 1turns drafting off per request, and answers in Chinese, Japanese, Korean and other scripts are drafted again. - DeepSeek on one NVIDIA GPU (#920): decode is back to v1.1.54's speed on PCs where the CPU handles experts in RAM faster than the GPU's link can bring them over. On our test PC it was about 75% faster than v1.1.57 from the second start after the update on (the first start measures once).
- Names: GLM-5.3-Flash's quants now show the model first ("GLM-5.3-Flash · Maya-S" ...); the setup ids are unchanged. GLM-5.3 (744B) is named in every model list.
- Opt-in:
MAYA_GLM_PREFILL_STABLE=1makes GLM prompt reads reproducible whatever the expert cache holds (for A/B checks; about 2-5% slower prompts). - Fixes:
- Codex and other Responses API clients: pictures with any
detailvalue are accepted (#914). - Windows with AMD graphics: GLM's RAM tier leaves room below the memory Windows lets a program pin, so the start no longer fails with "the warmed expert tables did not upload" (#924).
- DeepSeek EXL3 quants with their own F16 vision tower: pictures turn on by themselves, using DeepSeek's BF16 tower (#886).
- Loop guard: a finished short answer is no longer kept going, and a kept agent answer continues on a new paragraph (#921, thanks @TacoTakumi for #925).
- DeepSeek on one NVIDIA GPU: a tie in the PCIe lane's check no longer turns streaming off (#697).
- Setup: a very small extra card (such as a 2 GB display card) is left out of the automatic GPU choice instead of stopping the engine;
--gpusstill uses any card.
- Codex and other Responses API clients: pictures with any
Full list: CHANGELOG.md.
Supported by @vikcious, @ThatSimpleTech, @wjHunter and @davidfernengel.
Maya is free; if it helps you, you can sponsor it: https://github.com/sponsors/mw00