Step 5 Preview vs GLM 5.3

GLM 5.3 leads llmrun Score 130.1 to 128.0 (ranges overlap); neither fits 24 GB.

Model A · StepFun

Step 5 Preview

128.0llmrun Score

604.3B · 27B active · 1M context · Other · Sep 2026

ChatFunctions

Model B · Z.ai

GLM 5.3

130.1llmrun Score

753.3B · 41.8B active · 1M context · Other · Aug 2026

ChatFunctions

Which should you choose?

Choose GLM 5.3 if you want…

Higher llmrun Score
130.1 vs 128.0, ranges overlap

Step 5 Preview: no clear edge over GLM 5.3 in the data we have.

On your hardware

Each model at its default quant (Q4_K_M), a smaller one when it must. Estimates, ±20%.

MemoryStep 5 PreviewGLM 5.3

8 GB

RTX 4060 · 8 GB tier

Step 5 Preview

Doesn't fit

smallest quant needs 191.4 GB

GLM 5.3

Doesn't fit

smallest quant needs 256 GB

12 GB

RTX 3060 12GB · 12 GB tier

Step 5 Preview

Doesn't fit

smallest quant needs 191.4 GB

GLM 5.3

Doesn't fit

smallest quant needs 256 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Step 5 Preview

Doesn't fit

smallest quant needs 191.4 GB

GLM 5.3

Doesn't fit

smallest quant needs 256 GB

24 GBreference

RTX 4090 · 24 GB tier

Step 5 Preview

Doesn't fit

smallest quant needs 191.4 GB

GLM 5.3

Doesn't fit

smallest quant needs 256 GB

32 GB

RTX 5090 · 32 GB tier

Step 5 Preview

Doesn't fit

smallest quant needs 191.4 GB

GLM 5.3

Doesn't fit

smallest quant needs 256 GB

48 GB

RTX A6000 · 48 GB tier

Step 5 Preview

Doesn't fit

smallest quant needs 191.4 GB

GLM 5.3

Doesn't fit

smallest quant needs 256 GB

Mac 32 GB

Mac Mini M4 · Macs

Step 5 Preview

Doesn't fit

smallest quant needs 191.4 GB

GLM 5.3

Doesn't fit

smallest quant needs 256 GB

Mac 64 GB

Mac Studio M4 Max · Macs

Step 5 Preview

Doesn't fit

smallest quant needs 191.4 GB

GLM 5.3

Doesn't fit

smallest quant needs 256 GB

Mac 128 GB

Mac Studio M4 Max · Macs

Step 5 Preview

Doesn't fit

smallest quant needs 191.4 GB

GLM 5.3

Doesn't fit

smallest quant needs 256 GB

Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).

llmrun Score

with its 90% range · bars share one scale

Step 5 Preview GLM 5.3

Overall

Step 5 Preview

128.0124–132

GLM 5.3

130.1128–132

Coding

Step 5 Preview

no data

GLM 5.3

129.9124–136

Agents

Step 5 Preview

no data

GLM 5.3

133.5130–137

Math

Step 5 Preview

no data

GLM 5.3

128.5126–131

Science

Step 5 Preview

134.2122–147

GLM 5.3

130.6118–143

Reasoning

Step 5 Preview

no data

GLM 5.3

130.1124–136

Step 5 Preview · #8 of 101 open models · #6 of 98 that fit ≤512 GB

GLM 5.3 · #5 of 101 open models · #4 of 98 that fit ≤512 GB

Benchmarks

3 shared boards: Step 5 Preview leads 1, GLM 5.3 leads 1 · Benchmarks imported Oct 2026

BoardStep 5 PreviewGLM 5.3

SciCode

Step 5 Preview

58.9%#4/68 open

Lab-reportedEpoch AI · Sep 2026

GLM 5.3

59.0%#3/68 open

Lab-reportedEpoch AI · Aug 2026

CritPt

Step 5 Preview

20.9%#3/68 open

Lab-reportedEpoch AI · Sep 2026

GLM 5.3

19.1%#5/68 open

Lab-reportedEpoch AI · Aug 2026

ProofBench

Step 5 Preview

42.0%#9/27 open

Lab-reportedEpoch AI · Sep 2026

GLM 5.3

49.0%#8/27 open

Lab-reportedEpoch AI · Aug 2026

29 more boards (other shared and single-model boards)

Only GLM 5.3 (29)

VRAM by quantization

Memory to load the model and 2K context; below it, the total at 32K and 128K context. Lighter side in bold.

QuantStep 5 PreviewGLM 5.3

Q2_K

Step 5 Preview

283 GB182.5 GB file

32K 301 GB · 128K 360 GB

GLM 5.3

324 GB~320.2 GB file

32K 323 GB · 128K 332 GB

Q3_K_M

Step 5 Preview

324 GB~294.6 GB file

32K 343 GB · 128K 402 GB

GLM 5.3

371 GB~367.3 GB file

32K 370 GB · 128K 379 GB

Q4_K_M

Step 5 Preview

399 GB~362.6 GB file

32K 417 GB · 128K 476 GB

GLM 5.3

456 GB~452.0 GB file

32K 455 GB · 128K 464 GB

Q5_K_M

Step 5 Preview

474 GB~430.6 GB file

32K 492 GB · 128K 551 GB

GLM 5.3

541 GB~536.8 GB file

32K 540 GB · 128K 549 GB

Q6_K

Step 5 Preview

548 GB~498.6 GB file

32K 567 GB · 128K 626 GB

GLM 5.3

626 GB~621.5 GB file

32K 625 GB · 128K 634 GB

Q8_0

Step 5 Preview

665 GB~604.3 GB file

32K 683 GB · 128K 742 GB

GLM 5.3

758 GB801.4 GB file

32K 757 GB · 128K 765 GB

6 more quants

IQ2_XXS

Step 5 Preview

183 GB~166.2 GB file

32K 201 GB · 128K 260 GB

GLM 5.3

not listed

IQ2_M

Step 5 Preview

not listed

GLM 5.3

258 GB238.6 GB file

32K 257 GB · 128K 266 GB

IQ3_XXS

Step 5 Preview

not listed

GLM 5.3

296 GB281.7 GB file

32K 295 GB · 128K 304 GB

IQ3_M

Step 5 Preview

299 GB271.6 GB file

32K 318 GB · 128K 377 GB

GLM 5.3

not listed

IQ4_XS

Step 5 Preview

not listed

GLM 5.3

409 GB365.3 GB file

32K 408 GB · 128K 417 GB

BF16

Step 5 Preview

1330 GB~1208.7 GB file

32K 1348 GB · 128K 1407 GB

GLM 5.3

1511 GB1508.0 GB file

32K 1510 GB · 128K 1519 GB

How to run each

Step 5 Preview

Ollama · Q4_K_M

$ollama run hf.co/smalinin/Step-5-Preview-GGUF

All ways to run Step 5 Preview →

GLM 5.3

Ollama · Q4_K_M

$ollama run hf.co/unsloth/GLM-5.3-GGUF

All ways to run GLM 5.3 →

Specifications

Specifications of Step 5 Preview and GLM 5.3
Spec	Step 5 Preview	GLM 5.3
Publisher	StepFun	Z.ai
Parameters	604.3B	753.3B
Active parameters	27B per token	42B per token
Architecture	Step5ForConditionalGeneration	GlmMoeDsaForCausalLM
Context	1M tokens	1M tokens
Modalities	Chat, Function-calling	Chat, Function-calling
License	Other	Other
Released	Sep 2026	Aug 2026

Frequently Asked Questions

Which is better, Step 5 Preview or GLM 5.3?

GLM 5.3 leads llmrun Score 130.1 to 128.0 (ranges overlap); neither fits 24 GB. Choose GLM 5.3 for higher llmrun Score.

Which needs less VRAM, Step 5 Preview or GLM 5.3?

At Q4_K_M, Step 5 Preview requires 398.9 GB while GLM 5.3 needs 456.2 GB, making Step 5 Preview the easier model to run on your local setup.

Can I run Step 5 Preview or GLM 5.3 on a 16 GB GPU?

Step 5 Preview does not fit (smallest quant needs 191.4 GB); GLM 5.3 does not fit (smallest quant needs 256 GB).

Which has a longer context window, Step 5 Preview or GLM 5.3?

Step 5 Preview supports 1,048,576 tokens and GLM 5.3 supports 1,048,576 tokens.