modelrigs

GLM-5.3

The full-size sibling of GLM-5.3 Flash and the second-ranked open-weight model on aggregate benchmarks as of September 2026. Its parameter count and MLA geometry are taken from revision-pinned official weights and configuration metadata.

Z.aiMixture of expertscodingreasoning0 machines can run it
Total parameters
753.33B
Official spec sets memory need
Active parameters
40B
Official spec sets decode speed
Context
1M
Official spec tokens
4-bit weights
410 GB
Calculated before KV cache
This is a sparse mixture of experts. All 753.33B of weights must sit in memory, but only 40B are read per generated token — so it needs the memory of a 753.33B model and generates at roughly the speed of a 40B one. That is why large unified-memory machines suit it and fast 32 GB GPUs do not.
Model specification
Publisher
Z.ai Official spec
Architecture
Sparse mixture of experts Official spec
Total parameters
753.33B Official spec
Active parameters
40B per token Official spec
Context length
1,048,576 tokens Official spec
Attention ⓘ
MLA · 64 KV heads × 192 dim × 78 layers Official spec
Licence
MIT Official spec source
Specification confidence ⓘ
High · verified 2026-09-07 Official spec source
Released
1 Jul 2026 Official spec
Official source
Hugging Face
Quantizations and memory
QuantizationFormatBits/weightWeightsQuality kept
MLX 4-bitmlx4.5410.4 GB98.0%
Q4_K_Mdefaultgguf4.85438.1 GB98.5%
Q8_0gguf8.5760.4 GB99.9%
Weight sizes are computed from the parameter count and bits per weight plus a format-specific overhead for the layers that stay at higher precision — not read from a specific published file. Quality retention is an assumption, not a measured evaluation.
Quality benchmarks
BenchmarkCategoryScoreReported byDateSource
Terminal-Bench 2.1agentic88.2canonical model_repository31 Aug 2026link
DeepSWEcoding66.9canonical model_repository28 Aug 2026link
We show source metrics rather than deriving one opaque quality number. Different benchmarks measure genuinely different things, and collapsing them into a single score would hide exactly the disagreements worth seeing.
Recommendations
Cheapest that can run it
Nothing in the database qualifies.
Lowest purchase price among configurations where the model fits at some quantization in our catalogue. Speed is not considered.
Cheapest above 20 t/s
Nothing in the database qualifies.
20 tokens/second is roughly the point at which generation keeps pace with reading. Below it, interactive use feels like waiting.
Cheapest above 40 t/s
Nothing in the database qualifies.
40 tokens/second is the threshold most people describe as comfortable for coding agents, where output arrives faster than you can review it.
Fastest with real measurements
Nothing in the database qualifies.
Highest throughput among configurations with an actual published measurement rather than our estimate.
Best throughput per euro
Nothing in the database qualifies.
Highest decode tokens/second per EUR 1,000 of purchase price. Ignores running costs and resale — see the economics section for the full picture.
Hardware that runs GLM-5.30 measured, 0 estimated
0 of 0 rows
Hardware↕QuantMemory↕Decode▼Prefill↕ContextPrice↕FitConfidence↕
Nothing matches these filters.
Hosted alternatives for this exact model

These endpoints serve the same open weights, so comparing them against local ownership is a like-for-like economic question rather than a quality trade-off.

ProviderInput /1MOutput /1MVerifiedSource
Z.ai$1.40$4.406 Sept 2026link
Similar models
GLM-5.3 Flash
Z.ai · 321.323B (18B active) · MIT
DeepSeek-V4 Flash
DeepSeek · 304.18B (13B active) · MIT
DeepSeek-V3.2
DeepSeek · 685.397B (37B active) · MIT
Qwen3-Coder 30B-A3B
Alibaba Qwen · 30.532B (3.3B active) · Apache 2.0
Kimi K2.6
Moonshot AI · 1.0T (32B active) · Modified MIT
MiniMax M3
MiniMax · 427.04B (23B active) · Apache 2.0