Step 5 Preview vs GLM 4.5

Step 5 Preview leads llmrun Score 128.0 to 100.9; neither fits 24 GB.

Run Step 5 Preview in the cloud →

Model A · StepFun

Step 5 Preview

128.0llmrun Score

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

ChatFunctions

Model B · Z.ai

GLM 4.5

100.9llmrun Score

358.3B · 35.6B active · 128K context · MIT · Jul 2025

ChatFunctions

Which should you choose?

Choose Step 5 Preview if you want…

Higher llmrun Score
128.0 vs 100.9
Longer context window
1M vs 128K tokens
Newer release
Sep 2026 vs Jul 2025

Choose GLM 4.5 if you want…

Lighter on memory
215.6 vs 398.9 GB at Q4_K_M
More permissive license
MIT vs Other

On your hardware

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

MemoryStep 5 PreviewGLM 4.5

8 GB

RTX 4060 · 8 GB tier

Step 5 Preview

Doesn't fit

smallest quant needs 191.4 GB

GLM 4.5

Doesn't fit

smallest quant needs 101.4 GB

12 GB

RTX 3060 12GB · 12 GB tier

Step 5 Preview

Doesn't fit

smallest quant needs 191.4 GB

GLM 4.5

Doesn't fit

smallest quant needs 101.4 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Step 5 Preview

Doesn't fit

smallest quant needs 191.4 GB

GLM 4.5

Doesn't fit

smallest quant needs 101.4 GB

24 GBreference

RTX 4090 · 24 GB tier

Step 5 Preview

Doesn't fit

smallest quant needs 191.4 GB

GLM 4.5

Doesn't fit

smallest quant needs 101.4 GB

32 GB

RTX 5090 · 32 GB tier

Step 5 Preview

Doesn't fit

smallest quant needs 191.4 GB

GLM 4.5

Doesn't fit

smallest quant needs 101.4 GB

48 GB

RTX A6000 · 48 GB tier

Step 5 Preview

Doesn't fit

smallest quant needs 191.4 GB

GLM 4.5

Doesn't fit

smallest quant needs 101.4 GB

Mac 32 GB

Mac Mini M4 · Macs

Step 5 Preview

Doesn't fit

smallest quant needs 191.4 GB

GLM 4.5

Doesn't fit

smallest quant needs 101.4 GB

Mac 64 GB

Mac Studio M4 Max · Macs

Step 5 Preview

Doesn't fit

smallest quant needs 191.4 GB

GLM 4.5

Doesn't fit

smallest quant needs 101.4 GB

Mac 128 GB

Mac Studio M4 Max · Macs

Step 5 Preview

Doesn't fit

smallest quant needs 191.4 GB

GLM 4.5

IQ2_M · ~20 tok/s

123.8 GB · up to 16Kfits

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 4.5

Overall

Step 5 Preview

128.0124–132

GLM 4.5

100.997–105

Coding

Step 5 Preview

no data

GLM 4.5

98.789–109

Agents

Step 5 Preview

no data

GLM 4.5

105.499–112

Science

Step 5 Preview

134.2122–147

GLM 4.5

no data

Step 5 Preview · #9 of 106 open models · #6 of 102 that fit ≤512 GB

GLM 4.5 · #54 of 106 open models · #38 of 89 that fit ≤256 GB

Benchmarks

The two models share no benchmark board.

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

Only Step 5 Preview (3)

SciCode58.9%
CritPt20.9%
ProofBench42.0%

Only GLM 4.5 (8)

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 4.5

Q2_K

Step 5 Preview

283 GB182.5 GB file

32K 301 GB · 128K 360 GB

GLM 4.5

153 GB131.2 GB file

32K 158 GB · 128K 173 GB

Q3_K_S

Step 5 Preview

not listed

GLM 4.5

157 GB155.0 GB file

32K 162 GB · 128K 178 GB

Q3_K_M

Step 5 Preview

324 GB~294.6 GB file

32K 343 GB · 128K 402 GB

GLM 4.5

175 GB171.3 GB file

32K 180 GB · 128K 196 GB

Q4_0

Step 5 Preview

not listed

GLM 4.5

180 GB203.0 GB file

32K 185 GB · 128K 200 GB

Q4_K_M

Step 5 Preview

399 GB~362.6 GB file

32K 417 GB · 128K 476 GB

GLM 4.5

216 GB216.5 GB file

32K 220 GB · 128K 236 GB

Q5_K_M

Step 5 Preview

474 GB~430.6 GB file

32K 492 GB · 128K 551 GB

GLM 4.5

256 GB254.2 GB file

32K 261 GB · 128K 276 GB

Q6_K

Step 5 Preview

548 GB~498.6 GB file

32K 567 GB · 128K 626 GB

GLM 4.5

296 GB294.4 GB file

32K 301 GB · 128K 317 GB

Q8_0

Step 5 Preview

665 GB~604.3 GB file

32K 683 GB · 128K 742 GB

GLM 4.5

359 GB381.0 GB file

32K 364 GB · 128K 379 GB

14 more quants

IQ2_XXS

Step 5 Preview

183 GB~166.2 GB file

32K 201 GB · 128K 260 GB

GLM 4.5

99.2 GB115.9 GB file

32K 104 GB · 128K 119 GB

IQ2_XS

Step 5 Preview

not listed

GLM 4.5

108 GB101.8 GB file

32K 113 GB · 128K 128 GB

IQ2_S

Step 5 Preview

not listed

GLM 4.5

113 GB102.7 GB file

32K 117 GB · 128K 133 GB

IQ2_M

Step 5 Preview

not listed

GLM 4.5

122 GB122.4 GB file

32K 126 GB · 128K 142 GB

IQ3_XXS

Step 5 Preview

not listed

GLM 4.5

139 GB145.2 GB file

32K 144 GB · 128K 160 GB

IQ3_XS

Step 5 Preview

not listed

GLM 4.5

148 GB148.9 GB file

32K 153 GB · 128K 169 GB

IQ3_M

Step 5 Preview

299 GB271.6 GB file

32K 318 GB · 128K 377 GB

GLM 4.5

162 GB164.9 GB file

32K 167 GB · 128K 182 GB

Q3_K_L

Step 5 Preview

not listed

GLM 4.5

184 GB170.6 GB file

32K 189 GB · 128K 205 GB

IQ4_XS

Step 5 Preview

not listed

GLM 4.5

193 GB191.6 GB file

32K 198 GB · 128K 213 GB

IQ4_NL

Step 5 Preview

not listed

GLM 4.5

202 GB202.5 GB file

32K 207 GB · 128K 222 GB

Q4_1

Step 5 Preview

not listed

GLM 4.5

202 GB224.6 GB file

32K 207 GB · 128K 222 GB

Q4_K_S

Step 5 Preview

not listed

GLM 4.5

202 GB203.7 GB file

32K 207 GB · 128K 222 GB

Q5_K_S

Step 5 Preview

not listed

GLM 4.5

247 GB247.0 GB file

32K 252 GB · 128K 267 GB

BF16

Step 5 Preview

1330 GB~1208.7 GB file

32K 1348 GB · 128K 1407 GB

GLM 4.5

717 GB716.8 GB file

32K 722 GB · 128K 738 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 4.5

Ollama · Q4_K_M

$ollama run hf.co/unsloth/GLM-4.5-GGUF:Q4_K_M

All ways to run GLM 4.5 →

Specifications

Specifications of Step 5 Preview and GLM 4.5
Spec	Step 5 Preview	GLM 4.5
Publisher	StepFun	Z.ai
Parameters	604.3B	358.3B
Active parameters	27B per token	36B per token
Architecture	Step5ForConditionalGeneration	Glm4MoeForCausalLM
Context	1M tokens	128K tokens
Modalities	Chat, Function-calling	Chat, Function-calling
License	Other	MIT
Released	Sep 2026	Jul 2025

Frequently Asked Questions

Which is better, Step 5 Preview or GLM 4.5?

Step 5 Preview leads llmrun Score 128.0 to 100.9; neither fits 24 GB. Choose Step 5 Preview for higher llmrun Score and longer context window; choose GLM 4.5 for lighter on memory and more permissive license.

Which needs less VRAM, Step 5 Preview or GLM 4.5?

At Q4_K_M, Step 5 Preview requires 398.9 GB while GLM 4.5 needs 215.6 GB, making GLM 4.5 the easier model to run on your local setup.

Can I run Step 5 Preview or GLM 4.5 on a 16 GB GPU?

Step 5 Preview does not fit (smallest quant needs 191.4 GB); GLM 4.5 does not fit (smallest quant needs 101.4 GB).

Which has a longer context window, Step 5 Preview or GLM 4.5?

Step 5 Preview supports 1,048,576 tokens and GLM 4.5 supports 131,072 tokens.