GLM-5.3-Flash

About

What GLM-5.3-Flash is

An MLX build of the official zai-org/GLM-5.3-Flash — a 320B-total / 18B-active MoE, the first natively multimodal model in the GLM-5 series, built on the new glm5next hybrid architecture (sparse + linear attention with Manifold-Constrained Hyper-Connections) — quantized to MLX for Apple Silicon and the MLX CUDA backend. Five builds (2bit-lite / 2 / 3 / 4 / 6-bit) ship as subfolders, with the 4-bit build mirrored at the repo root, produced with OrcaSAQ (Sensitivity-Aware Quantization) — calibration-free and architecture-aware: sensitive tensors get more bits (shared experts +2, downproj +1), and every tensor that was not FP8 in the base release — the 34 linear-attention layers, the sparse indexer, hyper-connections, norms, embedtokens, lmhead, and the entire vision tower — is carried through in BF16. The four projections of the sparse-attention blocks were FP8 upstream and are quantized at the base width. Browse all models in the OrcaRouter Model Catalog; deployed as API here. Put this model to work reviewing your pull requests with OrcaCode Review. Available quantizations The repository root is a mirror of 4-bit/, so orcarouter/GLM-5.3-Flash-MLX resolves to the recommended default with no subfolder needed. Quantized from the official FP8 release. Bit-widths above are the base precision; the OrcaSAQ policy below raises sensitive tensors above the base. Group size is 64 for 4/6-bit, 32 for 2/3-bit (shared experts always use 64), and 128 throughout 2bit-lite. No 8-bit build was produced. 2bit-lite follows a separate, memory-first recipe — see below. OrcaSAQ — Sensitivity-Aware Quantization OrcaSAQ is a calibration-free, architecture-aware mixed-precision quantization method designed to preserve model quality while aggressively reducing memory footprint. Instead of running expensive calibration datasets or per-layer sensitivity searches, OrcaSAQ uses architectural and tensor-role priors to determine which weights are most sensitive to quantization. Critical components receive higher precision, while more quantization-tolerant tensors remain at the target base precision. For MoE architectures, for example, OrcaSAQ can preserve shared experts at base +2 bits, downproj

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How language models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys orcarouter-glm-5-3-flash for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (orcarouter-glm-5-3-flash below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"orcarouter-glm-5-3-flash","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Papers

Licence

Open weights

Sources

Weights & code

Explore

More language models