Skip to content
Weights Not Walls
Menu

zai-org

GLM-4.7-Flash

Reviewed
Size
31.2B 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
19 Jan 2026the date the repo was created
Context length
198k tokensfrom the model's config
Kind
Base model (no base model declared on the Hub)Glm4MoeLiteForCausalLM
On Hugging Face
zai-org/GLM-4.7-Flash1.2M downloads in the last 30 days, 1.9k likes

Scores

4 independent results on 2 eval sets
GPQA diamondRe-run by Epoch AI
  • default setting60.5%±2.930 Aug 2026, log
  • effort none45.1%±2.230 Aug 2026, log

Epoch's name: glm-4.7-flash. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results

OTIS Mock AIME 2024-2025Re-run by Epoch AI
  • default setting58.3%±6.630 Aug 2026, log
  • effort none25.0%±4.928 Aug 2026, log

Epoch's name: glm-4.7-flash. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 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: 0.41 GB, worked out from the model's config (zai-org/GLM-4.7-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

unsloth/GLM-4.7-Flash-GGUF (converted by unsloth), 248k downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
UD-IQ3_XXS12.0 GBfile size12.9 GB12.0 + 0.41 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:UD-IQ3_XXS
Ollama
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:UD-IQ3_XXS
Download
hf download unsloth/GLM-4.7-Flash-GGUF --include "GLM-4.7-Flash-UD-IQ3_XXS.gguf" --local-dir GLM-4.7-Flash-GGUF
Q3_K_S12.4 GBfile size13.3 GB12.4 + 0.41 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:Q3_K_S
Ollama
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:Q3_K_S
Download
hf download unsloth/GLM-4.7-Flash-GGUF --include "GLM-4.7-Flash-Q3_K_S.gguf" --local-dir GLM-4.7-Flash-GGUF
UD-Q3_K_XL12.8 GBfile size13.7 GB12.8 + 0.41 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:UD-Q3_K_XL
Ollama
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:UD-Q3_K_XL
Download
hf download unsloth/GLM-4.7-Flash-GGUF --include "GLM-4.7-Flash-UD-Q3_K_XL.gguf" --local-dir GLM-4.7-Flash-GGUF
Q3_K_M13.6 GBfile size14.5 GB13.6 + 0.41 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:Q3_K_M
Ollama
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:Q3_K_M
Download
hf download unsloth/GLM-4.7-Flash-GGUF --include "GLM-4.7-Flash-Q3_K_M.gguf" --local-dir GLM-4.7-Flash-GGUF
IQ4_XS15.2 GBfile size16.1 GB15.2 + 0.41 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:IQ4_XS
Ollama
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:IQ4_XS
Download
hf download unsloth/GLM-4.7-Flash-GGUF --include "GLM-4.7-Flash-IQ4_XS.gguf" --local-dir GLM-4.7-Flash-GGUF
MXFP4_MOE15.8 GBfile size16.7 GB15.8 + 0.41 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:MXFP4_MOE
Ollama
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:MXFP4_MOE
Download
hf download unsloth/GLM-4.7-Flash-GGUF --include "GLM-4.7-Flash-MXFP4_MOE.gguf" --local-dir GLM-4.7-Flash-GGUF
IQ4_NL16.0 GBfile size16.9 GB16.0 + 0.41 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:IQ4_NL
Ollama
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:IQ4_NL
Download
hf download unsloth/GLM-4.7-Flash-GGUF --include "GLM-4.7-Flash-IQ4_NL.gguf" --local-dir GLM-4.7-Flash-GGUF
Q4_016.0 GBfile size16.9 GB16.0 + 0.41 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:Q4_0
Ollama
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:Q4_0
Download
hf download unsloth/GLM-4.7-Flash-GGUF --include "GLM-4.7-Flash-Q4_0.gguf" --local-dir GLM-4.7-Flash-GGUF
Q4_K_S16.1 GBfile size17.0 GB16.1 + 0.41 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:Q4_K_S
Ollama
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:Q4_K_S
Download
hf download unsloth/GLM-4.7-Flash-GGUF --include "GLM-4.7-Flash-Q4_K_S.gguf" --local-dir GLM-4.7-Flash-GGUF
UD-Q4_K_XL16.3 GBfile size17.2 GB16.3 + 0.41 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:UD-Q4_K_XL
Ollama
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:UD-Q4_K_XL
Download
hf download unsloth/GLM-4.7-Flash-GGUF --include "GLM-4.7-Flash-UD-Q4_K_XL.gguf" --local-dir GLM-4.7-Flash-GGUF
Q4_K_M17.1 GBfile size18.0 GB17.1 + 0.41 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:Q4_K_M
Ollama
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:Q4_K_M
Download
hf download unsloth/GLM-4.7-Flash-GGUF --include "GLM-4.7-Flash-Q4_K_M.gguf" --local-dir GLM-4.7-Flash-GGUF
Q4_117.7 GBfile size18.6 GB17.7 + 0.41 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:Q4_1
Ollama
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:Q4_1
Download
hf download unsloth/GLM-4.7-Flash-GGUF --include "GLM-4.7-Flash-Q4_1.gguf" --local-dir GLM-4.7-Flash-GGUF
Q5_K_S19.4 GBfile size20.3 GB19.4 + 0.41 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:Q5_K_S
Ollama
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:Q5_K_S
Download
hf download unsloth/GLM-4.7-Flash-GGUF --include "GLM-4.7-Flash-Q5_K_S.gguf" --local-dir GLM-4.7-Flash-GGUF
Q5_K_M19.9 GBfile size20.9 GB19.9 + 0.41 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:Q5_K_M
Ollama
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:Q5_K_M
Download
hf download unsloth/GLM-4.7-Flash-GGUF --include "GLM-4.7-Flash-Q5_K_M.gguf" --local-dir GLM-4.7-Flash-GGUF
UD-Q5_K_XL20.2 GBfile size21.1 GB20.2 + 0.41 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:UD-Q5_K_XL
Ollama
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:UD-Q5_K_XL
Download
hf download unsloth/GLM-4.7-Flash-GGUF --include "GLM-4.7-Flash-UD-Q5_K_XL.gguf" --local-dir GLM-4.7-Flash-GGUF
Q6_K23.0 GBfile size23.9 GB23.0 + 0.41 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:Q6_K
Ollama
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:Q6_K
Download
hf download unsloth/GLM-4.7-Flash-GGUF --include "GLM-4.7-Flash-Q6_K.gguf" --local-dir GLM-4.7-Flash-GGUF
UD-Q6_K_XL24.4 GBfile size25.3 GB24.4 + 0.41 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:UD-Q6_K_XL
Ollama
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:UD-Q6_K_XL
Download
hf download unsloth/GLM-4.7-Flash-GGUF --include "GLM-4.7-Flash-UD-Q6_K_XL.gguf" --local-dir GLM-4.7-Flash-GGUF
Q8_029.7 GBfile size30.6 GB29.7 + 0.41 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:Q8_0
Ollama
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:Q8_0
Download
hf download unsloth/GLM-4.7-Flash-GGUF --include "GLM-4.7-Flash-Q8_0.gguf" --local-dir GLM-4.7-Flash-GGUF
UD-Q8_K_XL33.2 GBfile size34.1 GB33.2 + 0.41 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:UD-Q8_K_XL
Ollama
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:UD-Q8_K_XL
Download
hf download unsloth/GLM-4.7-Flash-GGUF --include "GLM-4.7-Flash-UD-Q8_K_XL.gguf" --local-dir GLM-4.7-Flash-GGUF
BF1655.8 GBfile size, 2 parts56.7 GB55.8 + 0.41 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF:BF16
Download
hf download unsloth/GLM-4.7-Flash-GGUF --include "BF16/GLM-4.7-Flash-BF16-*-of-00002.gguf" --local-dir GLM-4.7-Flash-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLX 6bitlmstudio-community/GLM-4.7-Flash-MLX-6bit22.7 GBfile size23.6 GB22.7 + 0.41 + 0.50Download page
MLX 8bitlmstudio-community/GLM-4.7-Flash-MLX-8bit29.6 GBfile size30.5 GB29.6 + 0.41 + 0.50Download page

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

FormatSizeMemory neededRepo
BF16original weights58.2 GBfile size59.1 GB58.2 + 0.41 + 0.50
hf download zai-org/GLM-4.7-Flash --local-dir GLM-4.7-Flash
Other conversions (16; 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

5 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
Cloudflare$0.06$0.40128knot given300.5 s97.4%yesyes
deepinfra$0.06$0.40198knot given380.6 s?yesyes
novita$0.07$0.40195knot given1000.9 s?yesno
featherless-ai???not given???not givennot given
zai-orgthe maker???not given860.7 s?yesno

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-4.7-Flash:cloudflare", "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.