Skip to content
localllm
日本語

antirez

glm-5.3-flash

Parameters
320.8B
Max context length
1,048,576
Architecture
glm5-next
llama.cpp
b11279+

About glm-5.3-flash

glm-5.3-flash (antirez) is a model published in GGUF format. GGUF files are published by antirez/glm-5.3-flash-gguf. It has about 320.8B parameters, the glm5-next architecture, a maximum context length of 1,048,576 tokens (values written in the GGUF).

There is one quantization, Q4_K, with a file size of 191 GB (actual size on Hugging Face).

Running Q4_K (191 GB) with an 8,192-token context needs an estimated 216 GB of memory, and an estimated 288 GB at 32,768 tokens.

File size and estimated memory per quantization

  • Up to 8 GB
  • Up to 16 GB
  • Up to 24 GB
  • Up to 48 GB
  • Up to 128 GB
  • More

File sizes are the actual values on Hugging Face. Memory is estimated for each context length (KV cache f16). The formula is in How memory is calculated.

All memory figures are Estimated (KV cache f16). It should run on a setup with at least this much VRAM (or Mac unified memory). Click a value to see the devices and models that fit that amount (Find by GPU / Mac).

About the "quality guide" (how far a quantization drifts from the original)

For each quantization type, how far the output drifts from the original model, grouped into six levels from values llama.cpp measured on Llama-3-8B.

The value is mean KLD (the difference between the original and quantized model in next-token probabilities); smaller means closer to the original. Quantizations made with an imatrix (importance data) come out slightly smaller. Levels use the value without an imatrix (or with one, for types that only have that).

These values were not measured on this model. Larger models and MoE models tend to drift less with the same type. Distributor-specific mixed types (such as UD-Q4_K_XL) cannot be matched by type name alone, so they show "-".

Quantization Quality guide KLD (no imatrix) KLD (imatrix) Size (Llama-3-8B)
Q8_0 Nearly identical 0.0014 - 7.96 GiB
Q6_K Very small 0.0055 - 6.14 GiB
Q5_K_M Very small 0.0108 - 5.33 GiB
Q5_K_S Small 0.0166 - 5.21 GiB
Q5_1 Small 0.0180 - 5.65 GiB
Q5_0 Small 0.0222 - 5.21 GiB
Q4_K_M Small 0.0313 0.0282 4.58 GiB
Q4_K_S Medium 0.0431 0.0320 4.37 GiB
IQ4_NL Small - 0.0357 4.35 GiB
IQ4_XS Small - 0.0363 4.14 GiB
Q4_1 Medium 0.0717 - 4.78 GiB
Q4_0 Medium 0.0719 - 4.34 GiB
Q3_K_L Medium 0.0872 0.0731 4.03 GiB
Q3_K_M Medium 0.1019 0.0844 3.74 GiB
IQ3_M Medium - 0.1025 3.53 GiB
IQ3_S Medium - 0.1113 3.42 GiB
IQ3_XS Large - 0.1387 3.28 GiB
IQ3_XXS Large - 0.1836 3.05 GiB
Q3_K_S Large 0.2282 0.1998 3.41 GiB
IQ2_M Large - 0.3260 2.74 GiB
Q2_K Very large 0.4451 0.3322 2.96 GiB
Q2_K_S Very large - 0.4034 2.96 GiB
IQ2_S Very large - 0.4392 2.56 GiB
IQ2_XS Very large - 0.5463 2.43 GiB
IQ2_XXS Very large - 0.8120 2.24 GiB
IQ1_M Very large - 1.3931 2.01 GiB
IQ1_S Very large - 2.2546 1.88 GiB

Source: llama.cpp (MIT), measured on Llama-3-8B against FP16, Wikitext-2, revision f364eb6f. Original table · Reading and choosing quantizations

GGUF source

antirez/glm-5.3-flash-gguf

Published by the original developer About this label

Last checked: Nov 11, 2026

Architecture
glm5-next
llama.cpp b11279 and later
Parameters
320.8B
Max context length
1,048,576
File size and memory per quantization for glm-5.3-flash (antirez/glm-5.3-flash-gguf)
Quantization File size Measured Quality guide 4,096 8,192 16,384 32,768 65,536 131,072 262,144 1,048,576 max
Q4_K 191 GB - 204 GB 216 GB 240 GB 288 GB 385 GB 578 GB 965 GB 3,284 GB 
Ollama  ollama run hf.co/antirez/glm-5.3-flash-gguf:Q4_K
llama.cpp  llama-server -hf antirez/glm-5.3-flash-gguf:Q4_K

How to run

Mainline llama.cpp can load this model's format (glm5-next) from b11279 (Sep 30, 2026) onward. Ollama and LM Studio bundle llama.cpp internally, so an older app fails to load it with errors such as "unknown model architecture". If that happens, update the app.

Example commands using Q4_K. To use another quantization, replace the name with one from the table above. How to run local LLMs

Ollama

Run it by pointing directly at the GGUF on Hugging Face.

ollama run hf.co/antirez/glm-5.3-flash-gguf:Q4_K

llama.cpp

Pass the repository and quantization name to llama-server (or llama-cli) with -hf.

llama-server -hf antirez/glm-5.3-flash-gguf:Q4_K

LM Studio

Paste antirez/glm-5.3-flash-gguf into the search box, download it, and choose the quantization from the file list.

Frequently asked questions

How much memory do I need to run glm-5.3-flash (Q4_K)?
The file size is 191 GB (measured). With a 8,192-token context, the estimated memory including the KV cache is 216 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.
Does glm-5.3-flash run in 8 GB, 12 GB, 16 GB or 24 GB of VRAM?
8 GB: no quantization fits; 12 GB: no quantization fits; 16 GB: no quantization fits; 24 GB: no quantization fits (estimated at 8,192 tokens with an f16 KV cache, files from the most-downloaded source).
What is the command to run glm-5.3-flash with Ollama?
Run "ollama run hf.co/antirez/glm-5.3-flash-gguf:Q4_K" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.