Skip to content
Weights Not Walls
Menu

zai-org

GLM-5.3-Flash

Reviewedaccepts images
Size
321B parameterscounted from the safetensors header on the Hub
Licence
unknown, MIT LicenseOur reading, check the licence: You can use, change and redistribute the model for any purpose, including commercially. Keep the copyright notice and the licence text with copies. You do not have to share your changes.
On the Hub since
25 Aug 2026the date the repo was created
Context length
1M tokensfrom the model's config
Kind
Base model (no base model declared on the Hub)Glm5NextForConditionalGeneration
On Hugging Face
zai-org/GLM-5.3-Flash6.4M downloads in the last 30 days, 3.3k likes

Scores

23 independent results on 17 eval sets
Chess PuzzlesRe-run by Epoch AI
  • effort max21.0%±4.113 Oct 2026, log

Epoch's name: glm-5.3-flash. Best closed model on this set: claude-fable-5-2_max, 79.0% (Anthropic). All 166 results

  • effort max17.1%±5.927 Aug 2026, Epoch AI

Epoch's name: glm-5.3-flash. Best closed model on this set: claude-fable-5-2_max, 100.0% (Anthropic). All 83 results

  • effort max55.8%±2.927 Aug 2026, Epoch AI

Epoch's name: glm-5.3-flash. Best closed model on this set: claude-fable-5-2_max, 95.1% (Anthropic). All 127 results

GPQA diamondRe-run by Epoch AI
  • effort max90.2%±1.726 Aug 2026, log

Epoch's name: glm-5.3-flash. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results

Mystery Game PuzzlesRe-run by Epoch AI
  • effort max8.0%±2.728 Aug 2026, Epoch AI

Epoch's name: glm-5.3-flash. Best closed model on this set: gpt-6.2-astra_max, 95.0% (OpenAI). All 148 results

OTIS Mock AIME 2024-2025Re-run by Epoch AI
  • effort max93.9%±2.226 Aug 2026, log

Epoch's name: glm-5.3-flash. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 results

APEX-AgentsReported

Epoch's name: glm-5.3-flash. Best closed model on this set: gemini-4-carbon_unknown, 84.2% (Google DeepMind). All 66 results

ARC-AGIReported

Epoch's name: glm-5.3-flash. Best closed model on this set: claude-fable-5_max, 98.5% (Anthropic). All 318 results

ARC-AGI-2Reported

Epoch's name: glm-5.3-flash. Best closed model on this set: gpt-6-astra_max, 95.0% (OpenAI). All 299 results

CritPtReported

Epoch's name: glm-5.3-flash. Best closed model on this set: gemini-4-carbon_high, 36.0% (Google DeepMind). All 271 results

CursorBenchReported

Epoch's name: glm-5.3-flash. Best closed model on this set: gemini-4-carbon_high, 60.4% (Google DeepMind). All 94 results

DeepSWEReported

Epoch's name: glm-5.3-flash. Best closed model on this set: gpt-6-astra_xhigh, 74.1% (OpenAI). All 69 results

FrontierCodeReported
  • effort max; Harness: devin-cli; Reasoning effort: max31.8%cognition.com

Epoch's name: glm-5.3-flash. Best closed model on this set: claude-opus-5-5_medium, 54.6% (Anthropic). All 46 results

FrontierSWEReported

Epoch's name: glm-5.3-flash. Best closed model on this set: claude-fable-5-2_max, 69.9% (Anthropic). All 25 results

Epoch's name: glm-5.3-flash. Best closed model on this set: claude-fable-5-1_max, 44.6% (Anthropic). All 22 results

ProofBenchReported

Epoch's name: glm-5.3-flash. Best closed model on this set: claude-fable-5-1_max, 100.0% (Anthropic). All 85 results

Epoch's name: glm-5.3-flash. Best closed model on this set: claude-fable-5_high, 95.0% (Anthropic). All 29 results

Claimed by the maker Claimed

The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.

Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.

Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.

Run it yourself

file sizes read from the Hub 19 Nov 2026

Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 1.4 GB, worked out from the model's config (zai-org/GLM-5.3-Flash), at 16-bit precision. Choose a machine above to see a verdict for each format. Method

GGUF for llama.cpp, Ollama, LM Studio and others

peasantsmith/GLM-5.3-Flash-Maya-GGUF (converted by peasantsmith), 1.5M downloads. Sizes are the real files on the Hub, all parts added up. For image input you also need the projector file vision/mmproj-GLM-5.3-Flash-F16.gguf (1.1 GB), not counted below.

FormatSizeMemory neededGet it
IQ1_S68.4 GBfile size, 2 parts70.2 GB68.4 + 1.4 + 0.50
Commands
llama.cpp
llama-server -hf peasantsmith/GLM-5.3-Flash-Maya-GGUF:IQ1_S
Download
hf download peasantsmith/GLM-5.3-Flash-Maya-GGUF --include "Maya-XS/GLM-5.3-Flash-Maya-XS-IQ1_S-*-of-00002.gguf" --local-dir GLM-5.3-Flash-Maya-GGUF
IQ2_XXS_S88.2 GBfile size, 3 parts90.1 GB88.2 + 1.4 + 0.50
Commands
llama.cpp
llama-server -hf peasantsmith/GLM-5.3-Flash-Maya-GGUF:IQ2_XXS_S
Download
hf download peasantsmith/GLM-5.3-Flash-Maya-GGUF --include "Maya-S24/GLM-5.3-Flash-Maya-S24-IQ2_XXS_S-*-of-00003.gguf" --local-dir GLM-5.3-Flash-Maya-GGUF
IQ2_XXS89.8 GBfile size, 3 parts91.7 GB89.8 + 1.4 + 0.50
Commands
llama.cpp
llama-server -hf peasantsmith/GLM-5.3-Flash-Maya-GGUF:IQ2_XXS
Download
hf download peasantsmith/GLM-5.3-Flash-Maya-GGUF --include "Maya-S-v2-IQ2_XXS/GLM-5.3-Flash-Maya-S-v2-IQ2_XXS-*-of-00003.gguf" --local-dir GLM-5.3-Flash-Maya-GGUF
IQ2_S108.0 GBfile size, 3 parts109.9 GB108.0 + 1.4 + 0.50
Commands
llama.cpp
llama-server -hf peasantsmith/GLM-5.3-Flash-Maya-GGUF:IQ2_S
Download
hf download peasantsmith/GLM-5.3-Flash-Maya-GGUF --include "Maya-M/GLM-5.3-Flash-Maya-M-IQ2_S-*-of-00003.gguf" --local-dir GLM-5.3-Flash-Maya-GGUF
IQ3_S145.6 GBfile size, 4 parts147.5 GB145.6 + 1.4 + 0.50
Commands
llama.cpp
llama-server -hf peasantsmith/GLM-5.3-Flash-Maya-GGUF:IQ3_S
Download
hf download peasantsmith/GLM-5.3-Flash-Maya-GGUF --include "Maya-L/GLM-5.3-Flash-Maya-L-IQ3_S-*-of-00004.gguf" --local-dir GLM-5.3-Flash-Maya-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLXJundot/GLM-5.3-Flash-oQ4e-mtp173.6 GBfile size175.5 GB173.6 + 1.4 + 0.50Download page
MLXorcarouter/GLM-5.3-Flash-MLX1057.3 GBfile size1059.2 GB1057.3 + 1.4 + 0.50Download page

Original weights size from the safetensors header, for vLLM, SGLang, Transformers

FormatSizeMemory neededRepo
F8_E4M3original weights305.7 GBfile size307.6 GB305.7 + 1.4 + 0.50
hf download zai-org/GLM-5.3-Flash --local-dir GLM-5.3-Flash
Other conversions (17; sizes not read)

The Hub tags 100 or more quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.

Run it by API

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

31 providers serve this model through the Hugging Face router. Prices are US dollars per million tokens. Precision is what the provider reports; a lower precision than the original weights can change answers. Live first, then cheapest output.

ProviderInOutContextPrecisionTokens/sFirst tokenUptime 24hToolsJSON
Relace$0.04$0.0781Mfp4841.0 s99.9%yesno
Wafer$0.042$0.181Mnvfp4440.7 s100.0%yesyes
Makora$0.14$0.241Mfp4940.5 s99.4%yesyes
Tenstorrent$0.075$0.25256kfp8373.6 s100.0%yesyes
Novita$0.084$0.281Mfp8402.0 s100.0%yesyes
Morph$0.10$0.301Mfp81030.6 s99.8%yesyes
Reka$0.12$0.301Mnot given1010.5 s100.0%yesyes
InferenceNet$0.11$0.351Mfp41380.4 s100.0%yesyes
DigitalOcean$0.11$0.381Mnot given801.0 s100.0%yesyes
CoreWeave$0.12$0.381Mnvfp41500.6 s99.0%yesyes
River$0.12$0.401Mnot given561.2 s99.7%yesyes
OpenInference$0.05$0.451Mfp41370.8 s100.0%yesyes
BaseTen$0.15$0.501Mfp8640.5 s99.9%yesyes
Cohere$0.15$0.501Mnvfp41450.7 s100.0%yesyes
Crusoe$0.15$0.501Mfp4960.7 s100.0%yesyes
DeepInfra$0.15$0.501Mfp4591.2 s100.0%yesyes
DekaLLM$0.10$0.501Mnot given312.5 s99.3%yesyes
Fireworks$0.15$0.501Mnot given801.6 s100.0%yesyes
Inceptron$0.15$0.501Mfp8790.5 s100.0%yesyes
Mistral$0.15$0.501Mnot given1420.9 s100.0%yesyes
Modal$0.15$0.501Mfp41100.4 s100.0%yesyes
Near AI$0.08$0.501Mfp8171.7 s99.9%yesyes
Nebius$0.15$0.501Mfp4720.7 s100.0%yesyes
Parasail$0.15$0.501Mfp8491.7 s100.0%yesyes
Particle AI$0.13$0.501Mnvfp4980.7 s100.0%yesyes
Together$0.15$0.501024knot given1390.5 s100.0%yesyes
Venice$0.15$0.501Mnot given650.7 s100.0%yesyes
Z.AIthe maker$0.15$0.501Mfp8461.8 s100.0%yesyes
Sail Research$0.17$0.631Mfp4472.6 s100.0%yesyes
featherless-ai???not given???not givennot given
zai-orgthe makerserves zai-org/GLM-5.3-Flash-BF16???not given451.3 s?yesyes

Through the router, with a Hugging Face token (the router bills your Hugging Face account). Change the name after the colon to pick another provider.

curl https://router.huggingface.co/v1/chat/completions \ -H "Authorization: Bearer $HF_TOKEN" -H "Content-Type: application/json" \ -d '{"model": "zai-org/GLM-5.3-Flash:relace", "messages": [{"role": "user", "content": "Hello"}]}'

Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.

Fine-tunes of this model

from our snapshot of the Hub

Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.

Planned for this page Not built yet

Try it in private chat
A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
Fine-tune it
Fine-tuning a few base models from this page and publishing the result here.
Creators and earnings
Pages for people who publish fine-tunes and adapters of this model, and what they earn.
Fund and bounties
Bounties for new open models, paid from a public fund. How the fund will work.
Contribute compute
How to give compute to open model work, with Akash.

Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.