NVIDIA Nemotron 3 Ultra 550B A55B BF16 vs GLM 4.7

NVIDIA Nemotron 3 Ultra 550B A55B BF16 and GLM 4.7 match in llmrun Score, with values of 109.9 versus 109.1; neither fits 24 GB.

Model A · NVIDIA

NVIDIA Nemotron 3 Ultra 550B A55B BF16

109.9llmrun Score

560.5B · 57B active · 256K context · Other · Jun 2026

ChatFunctions

Model B · Z.ai

GLM 4.7

109.1llmrun Score

358.3B · 35.6B active · 198K context · MIT · Dec 2025

ChatFunctions

Which should you choose?

Choose NVIDIA Nemotron 3 Ultra 550B A55B BF16 if you want…

Newer release
Jun 2026 vs Dec 2025

Choose GLM 4.7 if you want…

Lighter on memory
215.6 vs 370.0 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%.

MemoryNVIDIA Nemotron 3 Ultra 550B A55B BF16GLM 4.7

8 GB

RTX 4060 · 8 GB tier

NVIDIA Nemotron 3 Ultra 550B A55B BF16

Doesn't fit

smallest quant needs 178 GB

GLM 4.7

Doesn't fit

smallest quant needs 101.4 GB

12 GB

RTX 3060 12GB · 12 GB tier

NVIDIA Nemotron 3 Ultra 550B A55B BF16

Doesn't fit

smallest quant needs 178 GB

GLM 4.7

Doesn't fit

smallest quant needs 101.4 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

NVIDIA Nemotron 3 Ultra 550B A55B BF16

Doesn't fit

smallest quant needs 178 GB

GLM 4.7

Doesn't fit

smallest quant needs 101.4 GB

24 GBreference

RTX 4090 · 24 GB tier

NVIDIA Nemotron 3 Ultra 550B A55B BF16

Doesn't fit

smallest quant needs 178 GB

GLM 4.7

Doesn't fit

smallest quant needs 101.4 GB

32 GB

RTX 5090 · 32 GB tier

NVIDIA Nemotron 3 Ultra 550B A55B BF16

Doesn't fit

smallest quant needs 178 GB

GLM 4.7

Doesn't fit

smallest quant needs 101.4 GB

48 GB

RTX A6000 · 48 GB tier

NVIDIA Nemotron 3 Ultra 550B A55B BF16

Doesn't fit

smallest quant needs 178 GB

GLM 4.7

Doesn't fit

smallest quant needs 101.4 GB

Mac 32 GB

Mac Mini M4 · Macs

NVIDIA Nemotron 3 Ultra 550B A55B BF16

Doesn't fit

smallest quant needs 178 GB

GLM 4.7

Doesn't fit

smallest quant needs 101.4 GB

Mac 64 GB

Mac Studio M4 Max · Macs

NVIDIA Nemotron 3 Ultra 550B A55B BF16

Doesn't fit

smallest quant needs 178 GB

GLM 4.7

Doesn't fit

smallest quant needs 101.4 GB

Mac 128 GB

Mac Studio M4 Max · Macs

NVIDIA Nemotron 3 Ultra 550B A55B BF16

Doesn't fit

smallest quant needs 178 GB

GLM 4.7

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

NVIDIA Nemotron 3 Ultra 550B A55B BF16 GLM 4.7

Overall

NVIDIA Nemotron 3 Ultra 550B A55B BF16

109.9107–113

GLM 4.7

109.1105–113

Coding

NVIDIA Nemotron 3 Ultra 550B A55B BF16

104.099–109

GLM 4.7

101.388–115

Agents

NVIDIA Nemotron 3 Ultra 550B A55B BF16

102.188–116

GLM 4.7

105.898–114

Math

NVIDIA Nemotron 3 Ultra 550B A55B BF16

112.0105–119

GLM 4.7

111.1104–118

Science

NVIDIA Nemotron 3 Ultra 550B A55B BF16

111.8102–121

GLM 4.7

111.2102–120

Reasoning

NVIDIA Nemotron 3 Ultra 550B A55B BF16

116.4110–123

GLM 4.7

111.3100–122

NVIDIA Nemotron 3 Ultra 550B A55B BF16 · #26 of 100 open models · #23 of 96 that fit ≤512 GB

GLM 4.7 · #29 of 100 open models · #18 of 84 that fit ≤256 GB

Benchmarks

5 shared boards: NVIDIA Nemotron 3 Ultra 550B A55B BF16 leads 3, GLM 4.7 leads 2 · Benchmarks imported Oct 2026

BoardNVIDIA Nemotron 3 Ultra 550B A55B BF16GLM 4.7

GPQA Diamond

NVIDIA Nemotron 3 Ultra 550B A55B BF16

85.4%#20/98 open

IndependentEpoch AI · Jun 2026

GLM 4.7

83.3%#24/98 open

IndependentEpoch AI · Dec 2025

AIME 2024/2025

NVIDIA Nemotron 3 Ultra 550B A55B BF16

86.7%#18/86 open

IndependentEpoch AI · Jun 2026

GLM 4.7

83.3%#22/86 open

IndependentEpoch AI · Dec 2025

SciCode

NVIDIA Nemotron 3 Ultra 550B A55B BF16

40.3%#29/66 open

Lab-reportedEpoch AI · Jun 2026

GLM 4.7

45.1%#21/66 open

Lab-reportedEpoch AI · Dec 2025

CritPt

NVIDIA Nemotron 3 Ultra 550B A55B BF16

3.1%#24/66 open

Lab-reportedEpoch AI · Jun 2026

GLM 4.7

1.7%#29/66 open

Lab-reportedEpoch AI · Dec 2025

ProofBench

NVIDIA Nemotron 3 Ultra 550B A55B BF16

2.0%#23/26 open

Lab-reportedEpoch AI · Jun 2026

GLM 4.7

6.0%#20/26 open

Lab-reportedEpoch AI · Dec 2025

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

LMArena Text

NVIDIA Nemotron 3 Ultra 550B A55B BF16

1426.0#27/187 open

ArenaLMArena · Oct 2026

GLM 4.7

1441.3#18/187 open

ArenaLMArena · Oct 2026

Only NVIDIA Nemotron 3 Ultra 550B A55B BF16 (16)

Only GLM 4.7 (9)

VRAM by quantization

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

QuantNVIDIA Nemotron 3 Ultra 550B A55B BF16GLM 4.7

Q2_K

NVIDIA Nemotron 3 Ultra 550B A55B BF16

262 GB~238.2 GB file

32K 280 GB · 128K 338 GB

GLM 4.7

153 GB131.2 GB file

32K 158 GB · 128K 173 GB

Q3_K_S

NVIDIA Nemotron 3 Ultra 550B A55B BF16

not listed

GLM 4.7

157 GB155.0 GB file

32K 162 GB · 128K 178 GB

Q3_K_M

NVIDIA Nemotron 3 Ultra 550B A55B BF16

301 GB274.0 GB file

32K 319 GB · 128K 376 GB

GLM 4.7

175 GB171.3 GB file

32K 180 GB · 128K 196 GB

Q4_0

NVIDIA Nemotron 3 Ultra 550B A55B BF16

not listed

GLM 4.7

180 GB203.0 GB file

32K 185 GB · 128K 200 GB

Q4_K_M

NVIDIA Nemotron 3 Ultra 550B A55B BF16

370 GB359.2 GB file

32K 388 GB · 128K 446 GB

GLM 4.7

216 GB216.5 GB file

32K 220 GB · 128K 236 GB

Q5_K_M

NVIDIA Nemotron 3 Ultra 550B A55B BF16

439 GB426.5 GB file

32K 457 GB · 128K 515 GB

GLM 4.7

256 GB254.2 GB file

32K 261 GB · 128K 276 GB

Q6_K

NVIDIA Nemotron 3 Ultra 550B A55B BF16

509 GB460.7 GB file

32K 527 GB · 128K 585 GB

GLM 4.7

296 GB294.4 GB file

32K 301 GB · 128K 317 GB

Q8_0

NVIDIA Nemotron 3 Ultra 550B A55B BF16

617 GB584.3 GB file

32K 635 GB · 128K 692 GB

GLM 4.7

359 GB381.0 GB file

32K 364 GB · 128K 379 GB

16 more quants

IQ2_XXS

NVIDIA Nemotron 3 Ultra 550B A55B BF16

170 GB193.8 GB file

32K 188 GB · 128K 245 GB

GLM 4.7

99.2 GB115.9 GB file

32K 104 GB · 128K 119 GB

IQ2_XS

NVIDIA Nemotron 3 Ultra 550B A55B BF16

185 GB169.5 GB file

32K 203 GB · 128K 261 GB

GLM 4.7

108 GB101.5 GB file

32K 113 GB · 128K 128 GB

IQ2_S

NVIDIA Nemotron 3 Ultra 550B A55B BF16

not listed

GLM 4.7

113 GB102.3 GB file

32K 117 GB · 128K 133 GB

IQ2_M

NVIDIA Nemotron 3 Ultra 550B A55B BF16

208 GB194.0 GB file

32K 226 GB · 128K 284 GB

GLM 4.7

122 GB122.4 GB file

32K 126 GB · 128K 142 GB

IQ3_XXS

NVIDIA Nemotron 3 Ultra 550B A55B BF16

239 GB223.3 GB file

32K 257 GB · 128K 315 GB

GLM 4.7

139 GB145.1 GB file

32K 144 GB · 128K 160 GB

IQ3_XS

NVIDIA Nemotron 3 Ultra 550B A55B BF16

not listed

GLM 4.7

148 GB148.7 GB file

32K 153 GB · 128K 169 GB

IQ3_S

NVIDIA Nemotron 3 Ultra 550B A55B BF16

262 GB250.5 GB file

32K 280 GB · 128K 338 GB

GLM 4.7

153 GB154.6 GB file

32K 158 GB · 128K 173 GB

IQ3_M

NVIDIA Nemotron 3 Ultra 550B A55B BF16

not listed

GLM 4.7

162 GB164.8 GB file

32K 167 GB · 128K 182 GB

Q3_K_L

NVIDIA Nemotron 3 Ultra 550B A55B BF16

not listed

GLM 4.7

184 GB170.6 GB file

32K 189 GB · 128K 205 GB

IQ4_XS

NVIDIA Nemotron 3 Ultra 550B A55B BF16

331 GB286.1 GB file

32K 349 GB · 128K 407 GB

GLM 4.7

193 GB191.6 GB file

32K 198 GB · 128K 213 GB

IQ4_NL

NVIDIA Nemotron 3 Ultra 550B A55B BF16

347 GB294.2 GB file

32K 365 GB · 128K 423 GB

GLM 4.7

202 GB202.5 GB file

32K 207 GB · 128K 222 GB

Q4_1

NVIDIA Nemotron 3 Ultra 550B A55B BF16

not listed

GLM 4.7

202 GB224.6 GB file

32K 207 GB · 128K 222 GB

Q4_K_S

NVIDIA Nemotron 3 Ultra 550B A55B BF16

347 GB327.7 GB file

32K 365 GB · 128K 423 GB

GLM 4.7

202 GB203.7 GB file

32K 207 GB · 128K 222 GB

Q4_K_L

NVIDIA Nemotron 3 Ultra 550B A55B BF16

not listed

GLM 4.7

220 GB219.1 GB file

32K 225 GB · 128K 240 GB

Q5_K_S

NVIDIA Nemotron 3 Ultra 550B A55B BF16

424 GB391.7 GB file

32K 442 GB · 128K 500 GB

GLM 4.7

247 GB247.0 GB file

32K 252 GB · 128K 267 GB

BF16

NVIDIA Nemotron 3 Ultra 550B A55B BF16

1233 GB1099.0 GB file

32K 1251 GB · 128K 1309 GB

GLM 4.7

717 GB716.8 GB file

32K 722 GB · 128K 738 GB

How to run each

NVIDIA Nemotron 3 Ultra 550B A55B BF16

Ollama · Q4_K_M

$ollama run hf.co/unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF:Q4_K_M

All ways to run NVIDIA Nemotron 3 Ultra 550B A55B BF16 →

GLM 4.7

Ollama · Q4_K_M

$ollama run hf.co/unsloth/GLM-4.7-GGUF:Q4_K_M

All ways to run GLM 4.7 →

Specifications

Specifications of NVIDIA Nemotron 3 Ultra 550B A55B BF16 and GLM 4.7
Spec	NVIDIA Nemotron 3 Ultra 550B A55B BF16	GLM 4.7
Publisher	NVIDIA	Z.ai
Parameters	560.5B	358.3B
Active parameters	57B per token	36B per token
Architecture	NemotronHForCausalLM	Glm4MoeForCausalLM
Context	256K tokens	198K tokens
Modalities	Chat, Function-calling	Chat, Function-calling
License	Other	MIT
Released	Jun 2026	Dec 2025

Frequently Asked Questions

Which is better, NVIDIA Nemotron 3 Ultra 550B A55B BF16 or GLM 4.7?

NVIDIA Nemotron 3 Ultra 550B A55B BF16 and GLM 4.7 match in llmrun Score, with values of 109.9 versus 109.1; neither fits 24 GB. Choose NVIDIA Nemotron 3 Ultra 550B A55B BF16 for newer release; choose GLM 4.7 for lighter on memory and more permissive license.

Which needs less VRAM, NVIDIA Nemotron 3 Ultra 550B A55B BF16 or GLM 4.7?

At Q4_K_M, NVIDIA Nemotron 3 Ultra 550B A55B BF16 requires 370.0 GB while GLM 4.7 needs 215.6 GB, making GLM 4.7 the easier model to run on your local setup.

Can I run NVIDIA Nemotron 3 Ultra 550B A55B BF16 or GLM 4.7 on a 16 GB GPU?

NVIDIA Nemotron 3 Ultra 550B A55B BF16 does not fit (smallest quant needs 178 GB); GLM 4.7 does not fit (smallest quant needs 101.4 GB).

Which has a longer context window, NVIDIA Nemotron 3 Ultra 550B A55B BF16 or GLM 4.7?

NVIDIA Nemotron 3 Ultra 550B A55B BF16 supports 262,144 tokens and GLM 4.7 supports 202,752 tokens.