GLM GGUF models

1459 GGUF models in the GLM family, quantized by 464 uploaders. Sizes run from 2M to 5632B parameters. The longest trained context is 1024K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
GL
GLM 5.3 Flash
GLM · unsloth
Params320B
Context1024K
Smallest93.1 GB
Vision
GL
GLM 5.3 Flash Maya
GLM · peasantsmith
Params370B
Context64K
Smallest0.0 GB
Vision
GL
orcarouter GLM 5.3 Flash Uncensored
GLM · BoldingBuilds
Params321B
Context1024K
Smallest97.1 GB
Vision
GL
GLM 5.3
GLM · unsloth
Params754B
Context1024K
Smallest216.7 GB
GGUF
GL
Glm-4.7-Flash
GLM · unsloth
Params30B
Context198K
Q4_K_M18.3 GB
GGUF
GL
GLM 5.2
GLM · unsloth
Params754B
Context1024K
Q4_K_M465.8 GB
GGUF
GL
GLM-5.3-Flash Vision Encoder
GLM · antirez
Params321B
Context—
Smallest1.1 GB
GGUF
GL
GLM-5.3-Flash
GLM · GCSA-AiLab
Params313B
Context1024K
Smallest137.1 GB
Vision
GL
GLM 5.3 Flash
GLM · huihui-ai
Params321B
Context1024K
Smallest93.1 GB
Vision
GL
GLM OCR
GLM · ggml-org
Params891M
Context128K
Smallest1.0 GB
Vision
GL
Glm-4.5-Air
GLM · unsloth
Params110B
Context128K
Q4_K_M73.0 GB
GGUF
GL
GLM 5.3 Flash GGUF DGX Spark
GLM · autotrust
Params279B
Context1024K
Smallest84.9 GB
GGUF
GL
Glm-4.6V-Flash
GLM · unsloth
Params9.4B
Context128K
Q4_K_M6.2 GB
Vision
GL
Glm 5.3 Flash Reap50 Fp8 Pass2
GLM · patrickbdevaney
Params165B
Context1024K
Q4_K_M99.3 GB
ReasoningTool useVision
GL
GLM 4.7 Flash Uncensored Heretic NEO CODE Imatrix MAX
GLM · DavidAU
Params29.9B
Context198K
Q4_K_M18.5 GB
CodingReasoningRoleplay
GL
Zai org_GLM 4.7 Flash
GLM · lmstudio-community
Params30B
Context198K
Q4_K_M18.1 GB
GGUF
GL
GLM 5.3 Flash UNCENSORED
GLM · AliceThirty
Params320B
Context1024K
Smallest108.7 GB
Vision
GL
GLM 4.7 Flash
GLM · ggml-org
Params30B
Context198K
Smallest18.2 GB
GGUF
GL
GLM 5.3 Flash BF16
GLM · vcruz305
Params321B
Context1024K
Q4_K_M192.9 GB
Vision
GL
GLM 4.7 Flash
GLM · bartowski
Params30B
Context198K
Q4_K_M18.5 GB
GGUF
GL
GLM 5.3 Flash Strata Q2Q3 Experts
GLM · lte-ai
Params292B
Context1024K
Smallest63.2 GB
GGUF
GL
GLM 5.3 Flash CYBERSECURITY
GLM · SyndicateLabs
Params313B
Context1024K
Q4_K_M195.5 GB
GGUF
GL
Glm-4.6V
GLM · unsloth
Params107B
Context128K
Q4_K_M70.6 GB
Vision
GL
Zai org_GLM 4.6V Flash
GLM · lmstudio-community
Params9.4B
Context128K
Q4_K_M6.2 GB
Vision
GL
GLM 5.3 Flash Maya M Derisked IQ2 S
GLM · peasantsmith
Params321B
Context1024K
Smallest116.0 GB
GGUF
GL
GLM 5.3 Flash Coder RCO 152E
GLM · lapadatbogdan
Params170B
Context1024K
Q4_K_M102.6 GB
CodingReasoningTool use
GL
glm 5.3
GLM · antirez
Params754B
Context1024K
Smallest211.1 GB
GGUF
GL
Models Zai Org GLM 4.6V Flash
GLM · MaziyarPanahi
Params9.4B
Context128K
Q4_K_M6.2 GB
GGUF
GL
cerebras/GLM-4.7-Flash-REAP-23B-A3B
GLM · unsloth
Params23B
Context198K
Q4_K_M14.1 GB
GGUF
GL
Glm 4 9b Chat
GLM · QuantFactory
Params9.4B
Context128K
Q4_K_M6.3 GB
GGUF

About the GLM GGUF models

GLM is represented on ggufmodels.com by 1,459 GGUF models, quantized by 464 uploaders on Hugging Face. The most downloaded are GLM 5.3 Flash, GLM 5.3 Flash Maya and orcarouter GLM 5.3 Flash Uncensored. Parameter counts run from 2M to 5632B, and the longest trained context window is 1024K tokens.

A Q4_K_M file of a GLM model is between 0.1 to 492.8 GB, which is the quant most people start with. Most files come from mradermacher (307), Thireus (306) and bartowski (29). The quants you will meet most often are Q4_K_M (659), Q6_K (527), Q5_K_M (502) and Q2_K (494), where the number is how many models offer that quant.

Frequently asked questions

Which GLM GGUF should I download?

The most downloaded GLM GGUF here is GLM 5.3 Flash. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a GLM model need?

Q4_K_M files of GLM models on this site range from 0.1 to 492.8 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do GLM GGUF files come from?

The most common quantizers here are mradermacher, Thireus and bartowski. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing