ThinkFacility Sign in
  1. Can I run it locally?
  2. GLM

GLM VRAM requirements: can I run GLM-5.3 or GLM-5.2 locally?

GLM-5.3 and GLM-5.2 are 754 billion parameters each, 467 GB at a 4-bit quant. Here's what that means for a Mac Studio, and the two Flash models that fit far smaller machines.

Check your machine

Won't fit 201 GB

Weights, cache and overhead add up to more than the card and the RAM together.

  • Weights 200 GB
  • Context cache 0.6 GB
  • Overhead 0.8 GB
  • Fast memory
  • With system RAM

What we found

GLM-5.3 and 5.2 are the same size, so one answer covers both. At 4-bit that's a 512 GB Mac Studio with its GPU memory limit raised, and the smallest file, UD-IQ1_S (217 GB), still comes to 221 GB with a 32K context.

GLM-5.3 Flash is where it gets interesting. Three quarters of its layers use linear attention, so a million tokens of context costs 14.9 GB of cache. Full GLM-5.3 would need 115 GB for the same million. Its smallest file, UD-IQ1_S (93.1 GB), fits a DGX Spark or a 128 GB Mac.

For a single 24 GB card, GLM-4.7 Flash is the GLM that fits: 20.9 GB with a 32K context. Like DeepSeek it caches a compressed latent instead of full keys and values, which is why its cache stays small.

One detail for the GLM-5 models: their sparse attention keeps an extra indexer key for every token, and we count it in the cache.

Hardware that runs it

The biggest model on this page each machine holds whole with a 32K context, at the best file that fits. Which one to buy is in our GPU guide for local LLMs.

As an Amazon Associate we earn from qualifying purchases.

MachineRuns Check price on Amazon
16 GB graphics cardGeForce RTX 5060 Ti 16 GB, GeForce RTX 5070 Ti, GeForce RTX 5080GLM-4.6V Flash Q8_0and 1 more of the 7 here
ASUS Dual RTX 5060 Ti 16GB OCASUS Prime RTX 5070 Ti 16GB OCASUS Prime RTX 5080 EVO 16GB OC
24 GB graphics cardRadeon RX 7900 XTX, Intel Arc Pro B60GLM-4.7 Flash Q5_K_Mand 1 more of the 7 here
Compare in the guide
32 GB graphics cardGeForce RTX 5090, Radeon AI PRO R9700GLM-4.7 Flash Q6_Kand 1 more of the 7 here
Compare in the guide
48 GB workstation cardRTX PRO 5000 BlackwellGLM-4.7 Flash Q8_0and 3 more of the 7 here
Compare in the guide
96 GB workstation cardRTX PRO 6000 Blackwell Workstation EditionGLM-4.5 Air Q5_K_Mand 4 more of the 7 here
Compare in the guide
Mac with 64 GB of unified memoryMac mini (M5 Pro, 64 GB), Mac Studio (M5 Max, 64 GB)GLM-4.7 Flash Q8_0and 3 more of the 7 here
Compare in the guide
Mac with 96 GB of unified memoryMac Studio (M5 Ultra, 96 GB)GLM-4.6V Q4_K_Mand 3 more of the 7 here
Compare in the guide
Mac with 128 GB of unified memoryMac Studio (M5 Max, 128 GB), MacBook Pro 14 (M5 Max, 128 GB)GLM-4.5 Air Q5_K_Mand 4 more of the 7 here
MacBook Pro 14 M5 Max
Mac Studio with 256 GBMac Studio (M5 Ultra, 256 GB)GLM-5.3 Flash UD-Q4_K_XLand 4 more of the 7 here
Compare in the guide
Mac Studio with 512 GBMac Studio (M5 Ultra, 512 GB)GLM-5.3 Flash Q8_0and 6 more of the 7 here
Compare in the guide
Ryzen AI Max+ 395 mini PC with 128 GBGMKtec EVO-X2, Beelink GTR9 Pro, HP Z2 Mini G1aGLM-4.5 Air Q5_K_Mand 4 more of the 7 here
GMKtec EVO-X2 128GB
DGX Spark or another GB10 box, 128 GBNVIDIA DGX Spark, ASUS Ascent GX10GLM-4.5 Air Q8_0and 4 more of the 7 here
Compare in the guide

GLM-5.3 Flash

321 billion parameters · mixture of experts, 8 of 288 active · up to 1M context · 818 thousand downloads in 30 days

GLM-5.3 Flash needs about 201 GB at UD-Q4_K_XL with a 32K-token context. The file itself is 200 GB, and the cache for 32K tokens adds 0.6 GB. No single consumer card holds it. A Mac with 256 GB of unified memory does, and a PC can split it between a GPU and system RAM. It routes each token through 8 of 288 experts, so it runs faster than its size suggests.

Only 11 of its 45 layers keep a growing cache (the rest carry a fixed-size state), so the full 1M context costs 14.9 GB of cache.

QuantFileAt 8KAt 32KSmallest GPUSmallest Mac
UD-IQ1_S93.1 GB94.2 GB94.5 GB96 GB96 GB*
UD-Q2_K_XL109 GB110 GB110 GBnone128 GB*
UD-Q3_K_XL148 GB149 GB149 GBnone256 GB
UD-Q4_K_XL200 GB201 GB201 GBnone256 GB
UD-Q5_K_XL240 GB241 GB242 GBnone256 GB*
UD-Q6_K_XL292 GB293 GB293 GBnone512 GB
Q8_0341 GB342 GB342 GBnone512 GB
BF16642 GB643 GB643 GBnonenone

Smallest GPU and Mac are for the 32K total. * with the Mac's GPU memory limit raised.

Sources: GGUF files · config.json

GLM-5.3

754 billion parameters · mixture of experts, 8 of 256 active · up to 1M context · 352 thousand downloads in 30 days

At UD-Q4_K_XL, the GLM-5.3 file is 467 GB, and with 32K tokens of context and runtime overhead it comes to about 472 GB. No single consumer card holds it. A Mac with 512 GB of unified memory does once you raise the GPU memory limit, and a PC can split it between a GPU and system RAM. It routes each token through 8 of 256 experts, so it runs faster than its size suggests.

It caches a compressed latent per token rather than full keys and values, about 107 KB a token, so the cache is small next to the weights: 115 GB at 1M.

QuantFileAt 8KAt 32KSmallest GPUSmallest Mac
UD-IQ1_S217 GB218 GB221 GBnone256 GB*
UD-Q2_K_XL254 GB256 GB258 GBnone256 GB*
UD-Q3_K_XL343 GB345 GB347 GBnone512 GB
UD-Q4_K_XL467 GB469 GB472 GBnone512 GB*
UD-Q5_K_XL562 GB564 GB567 GBnonenone
UD-Q6_K_XL684 GB686 GB689 GBnonenone
Q8_0801 GB803 GB806 GBnonenone
BF161,508 GB1,510 GB1,512 GBnonenone

Smallest GPU and Mac are for the 32K total. * with the Mac's GPU memory limit raised.

Sources: GGUF files · config.json

GLM-4.7 Flash

29.9 billion parameters · mixture of experts, 4 of 64 active · up to 198K context · 296 thousand downloads in 30 days

GLM-4.7 Flash needs about 20.9 GB at Q4_K_M with a 32K-token context. The file itself is 18.3 GB, and the cache for 32K tokens adds 1.8 GB. That fits a 20 GB card (RX 7900 XT). It routes each token through 4 of 64 experts, so it runs faster than its size suggests.

It caches a compressed latent per token rather than full keys and values, about 53 KB a token, so the cache is small next to the weights: 11.0 GB at 198K.

QuantFileAt 8KAt 32KSmallest GPUSmallest Mac
UD-TQ1_08.3 GB9.6 GB10.9 GB12 GB16 GB
UD-Q2_K_XL11.9 GB13.1 GB14.5 GB16 GB24 GB
UD-Q3_K_XL13.8 GB15.0 GB16.4 GB16 GB24 GB
Q4_K_M18.3 GB19.6 GB20.9 GB20 GB24 GB*
Q5_K_M21.4 GB22.7 GB24.0 GB24 GB32 GB*
Q6_K24.7 GB26.0 GB27.3 GB32 GB32 GB*
Q8_031.8 GB33.1 GB34.4 GB48 GB48 GB
BF1659.9 GB61.2 GB62.5 GB96 GB64 GB*

Smallest GPU and Mac are for the 32K total. * with the Mac's GPU memory limit raised.

Sources: GGUF files · config.json

GLM-5.2

754 billion parameters · mixture of experts, 8 of 256 active · up to 1M context · 33 thousand downloads in 30 days

At UD-Q4_K_M, the GLM-5.2 file is 466 GB, and with 32K tokens of context and runtime overhead it comes to about 470 GB. No single consumer card holds it. A Mac with 512 GB of unified memory does once you raise the GPU memory limit, and a PC can split it between a GPU and system RAM. It routes each token through 8 of 256 experts, so it runs faster than its size suggests.

It caches a compressed latent per token rather than full keys and values, about 107 KB a token, so the cache is small next to the weights: 115 GB at 1M.

QuantFileAt 8KAt 32KSmallest GPUSmallest Mac
UD-IQ1_S217 GB218 GB221 GBnone256 GB*
UD-Q2_K_XL254 GB256 GB258 GBnone256 GB*
UD-Q3_K_XL343 GB345 GB347 GBnone512 GB
UD-Q4_K_M466 GB468 GB470 GBnone512 GB*
UD-Q5_K_XL562 GB564 GB567 GBnonenone
UD-Q6_K_XL684 GB686 GB689 GBnonenone
Q8_0801 GB803 GB806 GBnonenone
BF161,508 GB1,510 GB1,512 GBnonenone

Smallest GPU and Mac are for the 32K total. * with the Mac's GPU memory limit raised.

Sources: GGUF files · config.json

GLM-4.5 Air

110 billion parameters · mixture of experts, 8 of 128 active · up to 128K context · 144 thousand downloads in 30 days

GLM-4.5 Air needs about 80.0 GB at Q4_K_M with a 32K-token context. The file itself is 73.0 GB, and the cache for 32K tokens adds 6.2 GB. That fits a RTX PRO 6000 (96 GB). It's a mixture-of-experts model (8 of 128 experts per token), which is why people run it with the experts parked in system RAM and the rest on a 24 GB card.

Every token of context adds 184 KB of cache, so the full 128K would put 24.7 GB on top of the weights.

QuantFileAt 8KAt 32KSmallest GPUSmallest Mac
UD-TQ1_038.3 GB40.6 GB45.2 GB48 GB48 GB*
UD-Q2_K_XL47.4 GB49.8 GB54.4 GB96 GB64 GB*
UD-Q3_K_XL54.8 GB57.1 GB61.8 GB96 GB64 GB*
Q4_K_M73.0 GB75.3 GB80.0 GB96 GB96 GB*
Q5_K_M83.5 GB85.9 GB90.5 GB96 GB96 GB*
Q6_K99.0 GB101 GB106 GBnone128 GB*
Q8_0117 GB120 GB124 GBnone128 GB*
BF16221 GB223 GB228 GBnone256 GB*

Smallest GPU and Mac are for the 32K total. * with the Mac's GPU memory limit raised.

Sources: GGUF files · config.json

GLM-4.6V Flash

9.4 billion parameters · up to 128K context · 78 thousand downloads in 30 days

At Q4_K_M, the GLM-4.6V Flash file is 6.2 GB, and with 32K tokens of context and runtime overhead it comes to about 8.3 GB. Even a 8 GB card (RTX 4060, RTX 3070, RX 7600) holds that. On a Mac, 16 GB of unified memory is enough.

The cache is the part that grows: 40 KB a token, or 5.4 GB if you use all 128K tokens it supports.

QuantFileAt 8KAt 32KSmallest GPUSmallest Mac
UD-IQ1_S3.2 GB4.4 GB5.4 GB8 GB16 GB
UD-Q2_K_XL4.2 GB5.4 GB6.4 GB8 GB16 GB
UD-Q3_K_XL5.1 GB6.3 GB7.3 GB8 GB16 GB
Q4_K_M6.2 GB7.3 GB8.3 GB8 GB16 GB
Q5_K_M7.1 GB8.2 GB9.2 GB12 GB16 GB
Q6_K8.3 GB9.4 GB10.4 GB12 GB16 GB
Q8_010.0 GB11.1 GB12.2 GB12 GB16 GB*
BF1618.8 GB20.0 GB21.0 GB20 GB24 GB*

Smallest GPU and Mac are for the 32K total. * with the Mac's GPU memory limit raised.

Sources: GGUF files · config.json

GLM-4.6V

107 billion parameters · mixture of experts, 8 of 128 active · up to 128K context · 30 thousand downloads in 30 days

GLM-4.6V needs about 71.4 GB at Q4_K_M before its context cache: the file is 70.6 GB and llama.cpp wants roughly 0.8 GB more to run it. That fits a RTX PRO 6000 (96 GB). On a Mac, 96 GB of unified memory is enough. It's a mixture-of-experts model (8 of 128 experts per token), which is why people run it with the experts parked in system RAM and the rest on a 24 GB card.

We don't compute the context cache for the glm4v_moe_text architecture yet, because its config describes an attention scheme we haven't matched to llama.cpp's cache, so the totals here are weights and overhead only.

QuantFileAt 8KAt 32KSmallest GPUSmallest Mac
UD-TQ1_036.8 GB37.6 GB37.6 GB48 GB48 GB
UD-Q2_K_XL45.8 GB46.6 GB46.6 GB48 GB48 GB*
UD-Q3_K_XL52.7 GB53.5 GB53.5 GB96 GB64 GB*
Q4_K_M70.6 GB71.4 GB71.4 GB96 GB96 GB
Q5_K_M80.8 GB81.6 GB81.6 GB96 GB96 GB*
Q6_K95.9 GB96.7 GB96.7 GB96 GB96 GB*
Q8_0114 GB114 GB114 GBnone128 GB*
BF16214 GB215 GB215 GBnone256 GB*

Smallest GPU and Mac are for the 32K total. * with the Mac's GPU memory limit raised.

Sources: GGUF files · config.json

How the numbers are worked out

Total memory is three parts added together. Weights are the exact size of the GGUF file on Hugging Face, all parts summed when a quant is split. The context cache (the KV cache) comes from each model's own config.json:

cache = layers × kv_heads × head_dim × 2 (K and V) × 2 bytes × tokens

Sliding-window layers stop at their window plus llama.cpp's 512-token batch. Linear-attention and Mamba layers keep a fixed state instead, which we add once. Latent-attention models (DeepSeek, Kimi, GLM-5) cache kv_lora_rank + rope dimensions per layer, the way llama.cpp does. Overhead is our allowance: 0.5 GB for the GPU context plus the output buffer, 512 × vocabulary × 4 bytes.

A "24 GB" card holds 24 GiB, which is 25.8 GB in the decimal units file sizes use, and we count it that way. Macs get the share Metal allows by default, two thirds of unified memory up to 32 GB and three quarters above (llama.cpp discussion 2182); CPU-only machines and the DGX Spark keep 4 GB back for the operating system. All of it assumes llama.cpp's defaults: an f16 cache and one conversation at a time. Quantizing the cache to q8_0 halves it.

Files are Unsloth's GGUF uploads, the most downloaded quantizations on Hugging Face, and the list refreshes daily from Hugging Face's API. A model joins when its repo passes 20,000 downloads in 30 days. Last checked November 10, 2026.