Scantist/GLM-5.3-SLIM-GGUF
text-generation · ♥ 1.1K · ↓ 4.9K
- Tasktext-generation
- Downloads13.5k
- Likes1317
- Licenseother
text-generation · ♥ 1.1K · ↓ 4.9K
**A GLM-5.3-class model that runs on a single NVIDIA B200, or on a Mac Studio with 192 GB or more of unified memory (with mlx-serve).** At 179.9 GB it is 24.6% smaller than the 256-expert UD-IQ2_M (238.6 GB), which does not fit in the memory of one B200 or a 192 GB Mac. On one B200 the whole model sits on the GPU and about 100K tokens of KV cache are left for up to 10 parallel requests; in our tests it scores 92.7%…
GLM-5.3 with a **192-expert MoE architecture found by neural architecture search (NAS)**: every MoE layer keeps 192 of the original 256 routed experts. The model is built from Unsloth's UD-IQ2_M GGUF quantization.
Excerpt from the model card on Hugging Face ↗.
Scantist/GLM-5.3-SLIM-GGUF was first seen on Hugging Face · Trending models on Nov 8, 2026. Since then it has appeared in 118 checks on 7 different days. Its best position was #16 of 30, reached on Nov 10, 00:42 UTC. It dropped off the list after Nov 14, 01:44 UTC.
Position on Hugging Face · Trending models at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 14, 01:44 UTC, after 7 days of trending.
#16 on Hugging Face · Trending models, on Nov 10, 00:42 UTC. Trendoday checks this list every 60 minutes.
It was first seen on Nov 8, 2026 and has been on the list on 7 days (118 checks) since.
It is tagged text-generation on Hugging Face and has 13.5k downloads under the other license.