GLM-5.3 Flash
Z.ai · zai-org/GLM-5.3-Flash
Q4 file 156.8 GB (UD-IQ4_XS) · runs well from 512 GB · Weights license: MIT
Quality
Quality · Overall
LiveBench 2026-06-25 · 0–100 · higher is better · this model outlined, #15 of 23
- Color = publisher
- Memory under review
Source: LiveBench 2026-06-25 · collected 2026-10-18 · open models without a score are not drawn (no score ≠ 0)
- LMArena · text · rating
- 1,476 ± 5Confidence interval 1,471–1,481 · 38,359 votes · rank 35 of the releaseLMArena 2026-10-22 · CC BY 4.0
LiveBench categories
This model's mean per category · 0–100
Source: LiveBench 2026-06-25 · collected 2026-10-18 · open models without a score are not drawn (no score ≠ 0)
Quality · LMArena · vision
LMArena 2026-10-19 · human-preference rating · higher is better · this model outlined
- Color = publisher
Source: LMArena 2026-10-19 · collected 2026-10-25 · dataset · CC BY 4.0 · models without a rating are not drawn (no rating ≠ 0)
1,271 ± 6 · LMArena · vision · Confidence interval 1,265–1,278 · 16,254 votes
Reported by the publisher
Run it
Run it
File UD-IQ4_XS · 156.8 GB · 5 parts · unsloth/GLM-5.3-Flash-GGUF · What is Q4?
llama-server -hf unsloth/GLM-5.3-Flash-GGUF:UD-IQ4_XS- Install llama.cpp
- Run the command above
- Ask at localhost:8080:
Explain what a context window is, in two sentences.
Quality × memory
Quality × memory
LiveBench 2026-06-25 overall vs. Q4 planning memory (log scale) · 19 open models
- This model
- Color = publisher
Memory = the model's own figure: parameters × 0.625 bytes + 20% working room, before any machine's reserve; with a chosen machine, the total there with its reserve (25% of memory, 2 to 8 GB; 2 GB per graphics card). An estimate, not measured VRAM. LiveBench 2026-06-25
Runs on
Fast memory holds it 1
The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.
Within memory, outside the fast part 1
Within the machine's memory, outside its fast part: on a graphics card the layers that do not fit run on the CPU from PC RAM (the listed RAM, or 32 GB assumed); on a Mac, above the macOS default GPU share. Not a speed figure.
One memory tier short 9
The same machines with the next memory size up would hold it in fast memory.
Show all 9
GLM-5.3 Flash is a text model from Z.ai with 320B parameters, 18B of them active per token (mixture of experts). It was released on August 26, 2026 and reads up to 1,048,576 tokens of context. Its Q4 weights plus working room come to about 240 GB before the machine's reserve; the smallest reference machine whose fast memory holds that is Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unified (~248 GB with its reserve). We collected 13 downloadable GGUF and MLX files from 2 publisher sources; the most downloaded GGUF source is unsloth's (1.6M downloads on the Hub). It scores 71.6 overall in LiveBench 2026-06-25. Its LMArena text rating is 1,476 ± 5 (release 2026-10-22), a separate human-preference scale.
Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Each card opens its hardware profile. Not a measured fit or speed.
On the reference machines
| Where Q4 sits | ||||
|---|---|---|---|---|
| Mac mini M2 · 8 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column | ~242 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No file in the previous column |
| Mac mini M4 · 16 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column | ~244 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No file in the previous column |
| Mac mini M4 · 24 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column | ~246 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No file in the previous column |
| Mac mini M4 · 32 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column | ~248 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No file in the previous column |
| Mac mini M5 Pro · 64 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column | ~248 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No file in the previous column |
| Mac Studio M5 Max · 128 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column | ~248 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No file in the previous column |
| Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unifiedFast memory holds itUD-IQ4_XSKV-cache formula for this architecture not reviewed | ~248 GB | Fast memory holds it | UD-IQ4_XS | KV-cache formula for this architecture not reviewed |
| RTX 4060 · 8 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column | ~242 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No file in the previous column |
| RTX 3060 · 12 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column | ~242 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No file in the previous column |
| RTX 5080 · 16 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column | ~242 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No file in the previous column |
| RTX 4090 · 24 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column | ~242 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No file in the previous column |
| RTX 5090 · 32 GB VRAMLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column | ~242 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No file in the previous column |
| DGX H100 · 8 × 80 GBFast memory holds itQ8_0KV-cache formula for this architecture not reviewed | ~256 GB | Fast memory holds it | Q8_0 | KV-cache formula for this architecture not reviewed |
The file column uses the site's quant ladder (Q8_0 to Q3_K_M, MLX 8 to 4-bit on a Mac): the largest collected file whose size × 1.2 plus the context cache and the machine's reserve fits the fast memory. Planning estimates, not measured runs.
Consider this MoE checkpoint when comparing language and reasoning models with published total and active parameter counts.
320B total and 18B active are different quantities. Runtime support and any image components still need verification.
Versions to download
Files you can download for this checkpoint. The section opens on the most downloaded collected GGUF source, unsloth (1.6M Hub downloads), at UD-IQ4_XS. On a Mac it opens on the most downloaded MLX source. Sizes are the Hub's published bytes. What is Q4?
unsloth · 1.6M downloads
unsloth/GLM-5.3-Flash-GGUF · UD-IQ4_XS/GLM-5.3-Flash-UD-IQ4_XS-00001-of-00005.gguf · 156.8 GB
Run this file
llama-server -hf unsloth/GLM-5.3-Flash-GGUF:UD-IQ4_XSlms get https://huggingface.co/unsloth/GLM-5.3-Flash-GGUF- Ollama: Ollama's documented hf.co form covers single-file GGUFs; this file has 5 parts
- mlx-lm: mlx-lm runs MLX repositories; pick the MLX version on a Mac
Quality scores on this page belong to the original checkpoint; these files are not scored or ranked. File sizes read 2026-10-23 · download counts read 2026-10-17 · commands: Hugging Face Hub docs: Use Ollama with any GGUF model · llama.cpp server README (-hf <user>/<model>[:quant]) · LM Studio docs: lms get with a Hugging Face URL · mlx-lm README (mlx_lm.generate --model)
Fine-tunes, adapters and other versions
- Quantized versions
- 235
- Fine-tunes
- 38
- Adapters · merges
- 7 · 4
Browse them on the Hugging Face model tree · read 2026-10-23
Uncensored and abliterated versions
Some community uploads remove the model's safety refusals. Quality may drop, the original publisher does not support them, claims about them are the uploader's, and the original license still applies. This site never recommends or ranks them.
48 derivative repositories have “uncensored” or “abliterated” in their name (read 2026-10-23).
Measured speed
No published measurement for this checkpoint
Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.
How to run
~240 GB of Q4 weights plus working room, before the machine's reserve. Formula: parameters × 0.625 bytes, plus 20% working allowance; each machine then adds its system reserve: 25% of unified or system memory, 2 to 8 GB, or 2 GB per GPU on dedicated cards. This is neither measured VRAM nor checkpoint download size.
Q4 planning estimate only. Check checkpoint format, runtime support, KV cache, context, batch size and offload before choosing hardware.
Evidence level: Generic estimate only; no execution reproduced by this site.
- Publisher sampling defaults
- temperature 1 · top_p 0.95generation_config.json · read 2026-10-23source
- Chat template markers
- tool calls · thinkingmarkers found in the template, not a test of the feature · read 2026-10-23source
Before downloading
- Check the exact checkpoint and license linked here.
- Confirm a compatible runtime and precision or quantization for your platform.
- Allow for context, batch size and any extra media components beyond the weights.
Technical details
What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.
- Checkpoint / version
- zai-org/GLM-5.3-Flash
- Task and modality
- language and reasoning · text + image
- Count and basis
- 320B · manufacturer specification · 18B active
- Context
- 1,048,576 tokens published for this modelzai-org/GLM-5.3-Flash config.json (Hugging Face) · read 2026-10-09source
- Architecture
- MoE
- Released
- New Released - Z.AI DEVELOPER DOCUMENT · read 2026-10-09source
- Runtime and precision
- No local execution verified.
- Languages
- en, zhModel card metadata · read 2026-10-25source
- Commercial use
- Allowed MIT license text (SPDX) · read 2026-10-18license text
Every stored field
- Revision checked
- eb9eb208eb0d988989d07a6a12d0fdeb5f52574a
- Architecture
- Glm5NextForConditionalGeneration
- Library
- transformers
- Hub task tag
- image-text-to-text
- Distributions in this group
- mlx-community/GLM-5.3-Flash-4bit
- Formats
- safetensors
- Repository created
- 2026-08-25creation is not the model's release
- Repository updated
- 2026-09-07a commit is not a release date
- Hub downloads (30 days) · likes
- 6,352,272 · 2,945this repository only · read 2026-10-25
- Read from the Hub page
- task, transformers class, task tags, file formatsHub overview and file listing · read 2026-10-18
- Catalog state
- Hub inventory current
The manufacturer lists 320B total and 18B active. Image input may require supporting components; the Q4 planning estimate is not a validated runtime requirement.
Sources
Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.
- Publisher checkpoint and model card
- Weight license and use terms
- Quality benchmark source · LiveBench 2026-06-25 overall
Catalog reviewed: 2026-09-30. Benchmark release: 2026-06-25; snapshot collected: 2026-10-18.








