Inkling 2 Small vs GLM 5.3 Flash

Inkling 2 Small leads llmrun Score 134.7 to 124.0; neither fits 24 GB.

Run Inkling 2 Small in the cloud →

Model A · Thinking Machines

Inkling 2 Small

134.7llmrun Score

594B · 17B active · 1M context · Apache 2.0 · Nov 2026

VisionChat

Model B · Z.ai

GLM 5.3 Flash

124.0llmrun Score

321.3B · 18.3B active · 1M context · MIT · Aug 2026

VisionFunctions

Which should you choose?

Choose Inkling 2 Small if you want…

Higher llmrun Score
134.7 vs 124.0
Stronger at reasoning
136.1 vs 127.4
Ahead on the benchmarks
3 of 4 shared boards
Also does chat
GLM 5.3 Flash doesn't list it

Choose GLM 5.3 Flash if you want…

Lighter on memory
194.6 vs 357.0 GB at Q4_K_M
Also does function-calling
Inkling 2 Small doesn't list it

On your hardware

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

MemoryInkling 2 SmallGLM 5.3 Flash

8 GB

RTX 4060 · 8 GB tier

Inkling 2 Small

Doesn't fit

smallest quant needs 166.1 GB

GLM 5.3 Flash

Doesn't fit

smallest quant needs 100.7 GB

12 GB

RTX 3060 12GB · 12 GB tier

Inkling 2 Small

Doesn't fit

smallest quant needs 166.1 GB

GLM 5.3 Flash

Doesn't fit

smallest quant needs 100.7 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Inkling 2 Small

Doesn't fit

smallest quant needs 166.1 GB

GLM 5.3 Flash

Doesn't fit

smallest quant needs 100.7 GB

24 GBreference

RTX 4090 · 24 GB tier

Inkling 2 Small

Doesn't fit

smallest quant needs 166.1 GB

GLM 5.3 Flash

Doesn't fit

smallest quant needs 100.7 GB

32 GB

RTX 5090 · 32 GB tier

Inkling 2 Small

Doesn't fit

smallest quant needs 166.1 GB

GLM 5.3 Flash

Doesn't fit

smallest quant needs 100.7 GB

48 GB

RTX A6000 · 48 GB tier

Inkling 2 Small

Doesn't fit

smallest quant needs 166.1 GB

GLM 5.3 Flash

Doesn't fit

smallest quant needs 100.7 GB

Mac 32 GB

Mac Mini M4 · Macs

Inkling 2 Small

Doesn't fit

smallest quant needs 166.1 GB

GLM 5.3 Flash

Doesn't fit

smallest quant needs 100.7 GB

Mac 64 GB

Mac Studio M4 Max · Macs

Inkling 2 Small

Doesn't fit

smallest quant needs 166.1 GB

GLM 5.3 Flash

Doesn't fit

smallest quant needs 100.7 GB

Mac 128 GB

Mac Studio M4 Max · Macs

Inkling 2 Small

Doesn't fit

smallest quant needs 166.1 GB

GLM 5.3 Flash

IQ2_S · ~41 tok/s

112.8 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

Inkling 2 Small GLM 5.3 Flash

Overall

Inkling 2 Small

134.7130–139

GLM 5.3 Flash

124.0122–126

Coding

Inkling 2 Small

no data

GLM 5.3 Flash

116.5112–121

Agents

Inkling 2 Small

no data

GLM 5.3 Flash

127.6123–132

Math

Inkling 2 Small

no data

GLM 5.3 Flash

121.4118–125

Science

Inkling 2 Small

no data

GLM 5.3 Flash

123.5112–136

Reasoning

Inkling 2 Small

136.1131–142

GLM 5.3 Flash

127.4124–131

Inkling 2 Small · #2 of 107 open models · #1 of 103 that fit ≤512 GB

GLM 5.3 Flash · #13 of 107 open models · #7 of 90 that fit ≤256 GB

Benchmarks

4 shared boards: Inkling 2 Small leads 3, GLM 5.3 Flash leads 1 · Benchmarks imported Nov 2026

BoardInkling 2 SmallGLM 5.3 Flash

ARC-AGI-2

Inkling 2 Small

81.7%#1/23 open

IndependentEpoch AI · Nov 2026

GLM 5.3 Flash

65.8%#4/23 open

IndependentEpoch AI · Aug 2026

SciCode

Inkling 2 Small

52.3%#10/74 open

Lab-reportedEpoch AI · Nov 2026

GLM 5.3 Flash

51.6%#12/74 open

Lab-reportedEpoch AI · Aug 2026

ARC-AGI

Inkling 2 Small

96.5%#1/23 open

IndependentEpoch AI · Nov 2026

GLM 5.3 Flash

91.0%#5/23 open

IndependentEpoch AI · Aug 2026

APEX-Agents

Inkling 2 Small

46.8%#11/22 open

Lab-reportedEpoch AI · Nov 2026

GLM 5.3 Flash

52.8%#5/22 open

Lab-reportedEpoch AI · Aug 2026

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

LMArena Text

Inkling 2 Small

1411.8#46/191 open

ArenaLMArena · Nov 2026

GLM 5.3 Flash

1475.3#5/191 open

ArenaLMArena · Nov 2026

LMArena WebDev

Inkling 2 Small

1647.1#4/58 open

ArenaLMArena · Nov 2026

GLM 5.3 Flash

1608.8#11/58 open

ArenaLMArena · Nov 2026

Only GLM 5.3 Flash (25)

VRAM by quantization

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

QuantInkling 2 SmallGLM 5.3 Flash

Q2_K

Inkling 2 Small

253 GB~252.4 GB file

32K 258 GB · 128K 272 GB

GLM 5.3 Flash

138 GB114.2 GB file

32K 161 GB · 128K 234 GB

Q3_K_M

Inkling 2 Small

290 GB~289.6 GB file

32K 295 GB · 128K 309 GB

GLM 5.3 Flash

158 GB149.1 GB file

32K 181 GB · 128K 254 GB

Q4_K_M

Inkling 2 Small

357 GB~356.4 GB file

32K 362 GB · 128K 376 GB

GLM 5.3 Flash

195 GB208.2 GB file

32K 217 GB · 128K 290 GB

Q5_K_M

Inkling 2 Small

424 GB~423.2 GB file

32K 428 GB · 128K 443 GB

GLM 5.3 Flash

231 GB244.7 GB file

32K 253 GB · 128K 326 GB

Q6_K

Inkling 2 Small

491 GB~490.1 GB file

32K 495 GB · 128K 510 GB

GLM 5.3 Flash

267 GB~265.1 GB file

32K 290 GB · 128K 362 GB

Q8_0

Inkling 2 Small

595 GB~594.0 GB file

32K 599 GB · 128K 614 GB

GLM 5.3 Flash

323 GB341.0 GB file

32K 346 GB · 128K 418 GB

8 more quants

IQ2_XXS

Inkling 2 Small

164 GB190.6 GB file

32K 168 GB · 128K 183 GB

GLM 5.3 Flash

90.2 GB101.8 GB file

32K 113 GB · 128K 185 GB

IQ2_XS

Inkling 2 Small

not listed

GLM 5.3 Flash

98.2 GB92.1 GB file

32K 121 GB · 128K 193 GB

IQ2_S

Inkling 2 Small

not listed

GLM 5.3 Flash

102 GB113.6 GB file

32K 125 GB · 128K 197 GB

IQ3_XXS

Inkling 2 Small

231 GB226.0 GB file

32K 235 GB · 128K 250 GB

GLM 5.3 Flash

126 GB120.4 GB file

32K 149 GB · 128K 221 GB

IQ3_S

Inkling 2 Small

not listed

GLM 5.3 Flash

138 GB149.6 GB file

32K 161 GB · 128K 234 GB

IQ3_M

Inkling 2 Small

not listed

GLM 5.3 Flash

146 GB150.7 GB file

32K 169 GB · 128K 242 GB

IQ4_XS

Inkling 2 Small

not listed

GLM 5.3 Flash

175 GB156.8 GB file

32K 197 GB · 128K 270 GB

BF16

Inkling 2 Small

1189 GB~1188.0 GB file

32K 1193 GB · 128K 1208 GB

GLM 5.3 Flash

644 GB641.6 GB file

32K 667 GB · 128K 740 GB

How to run each

Inkling 2 Small

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Inkling-2-Small-GGUF

All ways to run Inkling 2 Small →

GLM 5.3 Flash

Ollama · Q4_K_M

$ollama run hf.co/vultr/GLM-5.3-Flash-GGUF:Q4_K_M

All ways to run GLM 5.3 Flash →

Specifications

Specifications of Inkling 2 Small and GLM 5.3 Flash
Spec	Inkling 2 Small	GLM 5.3 Flash
Publisher	Thinking Machines	Z.ai
Parameters	594B	321.3B
Active parameters	17B per token	18B per token
Architecture	Inkling2ForConditionalGeneration	Glm5NextForConditionalGeneration
Context	1M tokens	1M tokens
Modalities	Vision, Chat	Vision, Function-calling
License	Apache 2.0	MIT
Released	Nov 2026	Aug 2026

Frequently Asked Questions

Which is better, Inkling 2 Small or GLM 5.3 Flash?

Inkling 2 Small leads llmrun Score 134.7 to 124.0; neither fits 24 GB. Choose Inkling 2 Small for higher llmrun Score and stronger at reasoning; choose GLM 5.3 Flash for lighter on memory and also does function-calling.

Which needs less VRAM, Inkling 2 Small or GLM 5.3 Flash?

At Q4_K_M, Inkling 2 Small requires 357.0 GB while GLM 5.3 Flash needs 194.6 GB, making GLM 5.3 Flash the easier model to run on your local setup.

Can I run Inkling 2 Small or GLM 5.3 Flash on a 16 GB GPU?

Inkling 2 Small does not fit (smallest quant needs 166.1 GB); GLM 5.3 Flash does not fit (smallest quant needs 100.7 GB).

Which has a longer context window, Inkling 2 Small or GLM 5.3 Flash?

Inkling 2 Small supports 1,048,576 tokens and GLM 5.3 Flash supports 1,048,576 tokens.