DeepSeek V4.1 Flash 1017 vs GLM 5.3 Flash

DeepSeek V4.1 Flash 1017 leads llmrun Score 133.2 to 124.1; neither fits 24 GB.

Model A · DeepSeek

DeepSeek V4.1 Flash 1017

133.2llmrun Score

763.2B · 16B active · 1M context · MIT · Oct 2026

Vision

Model B · Z.ai

GLM 5.3 Flash

124.1llmrun Score

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

VisionFunctions

Which should you choose?

Choose DeepSeek V4.1 Flash 1017 if you want…

Higher llmrun Score
133.2 vs 124.1
Stronger at reasoning
139.8 vs 127.4
Stronger at math
132.0 vs 121.4
Ahead on the benchmarks
9 of 9 shared boards

Choose GLM 5.3 Flash if you want…

Lighter on memory
194.6 vs 458.3 GB at Q4_K_M
Also does function-calling
DeepSeek V4.1 Flash 1017 doesn't list it

On your hardware

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

MemoryDeepSeek V4.1 Flash 1017GLM 5.3 Flash

8 GB

RTX 4060 · 8 GB tier

DeepSeek V4.1 Flash 1017

Doesn't fit

smallest quant needs 210.4 GB

GLM 5.3 Flash

Doesn't fit

smallest quant needs 100.7 GB

12 GB

RTX 3060 12GB · 12 GB tier

DeepSeek V4.1 Flash 1017

Doesn't fit

smallest quant needs 210.4 GB

GLM 5.3 Flash

Doesn't fit

smallest quant needs 100.7 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

DeepSeek V4.1 Flash 1017

Doesn't fit

smallest quant needs 210.4 GB

GLM 5.3 Flash

Doesn't fit

smallest quant needs 100.7 GB

24 GBreference

RTX 4090 · 24 GB tier

DeepSeek V4.1 Flash 1017

Doesn't fit

smallest quant needs 210.4 GB

GLM 5.3 Flash

Doesn't fit

smallest quant needs 100.7 GB

32 GB

RTX 5090 · 32 GB tier

DeepSeek V4.1 Flash 1017

Doesn't fit

smallest quant needs 210.4 GB

GLM 5.3 Flash

Doesn't fit

smallest quant needs 100.7 GB

48 GB

RTX A6000 · 48 GB tier

DeepSeek V4.1 Flash 1017

Doesn't fit

smallest quant needs 210.4 GB

GLM 5.3 Flash

Doesn't fit

smallest quant needs 100.7 GB

Mac 32 GB

Mac Mini M4 · Macs

DeepSeek V4.1 Flash 1017

Doesn't fit

smallest quant needs 210.4 GB

GLM 5.3 Flash

Doesn't fit

smallest quant needs 100.7 GB

Mac 64 GB

Mac Studio M4 Max · Macs

DeepSeek V4.1 Flash 1017

Doesn't fit

smallest quant needs 210.4 GB

GLM 5.3 Flash

Doesn't fit

smallest quant needs 100.7 GB

Mac 128 GB

Mac Studio M4 Max · Macs

DeepSeek V4.1 Flash 1017

Doesn't fit

smallest quant needs 210.4 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

DeepSeek V4.1 Flash 1017 GLM 5.3 Flash

Overall

DeepSeek V4.1 Flash 1017

133.2131–136

GLM 5.3 Flash

124.1122–126

Coding

DeepSeek V4.1 Flash 1017

no data

GLM 5.3 Flash

116.9112–122

Agents

DeepSeek V4.1 Flash 1017

no data

GLM 5.3 Flash

127.3123–132

Math

DeepSeek V4.1 Flash 1017

132.0129–135

GLM 5.3 Flash

121.4118–125

Science

DeepSeek V4.1 Flash 1017

no data

GLM 5.3 Flash

123.5111–136

Reasoning

DeepSeek V4.1 Flash 1017

139.8133–146

GLM 5.3 Flash

127.4124–131

DeepSeek V4.1 Flash 1017 · #1 of 101 open models · #1 of 98 that fit ≤512 GB

GLM 5.3 Flash · #11 of 101 open models · #6 of 86 that fit ≤256 GB

Benchmarks

9 shared boards: DeepSeek V4.1 Flash 1017 leads 9, GLM 5.3 Flash leads 0 · Benchmarks imported Oct 2026

BoardDeepSeek V4.1 Flash 1017GLM 5.3 Flash

GPQA Diamond

DeepSeek V4.1 Flash 1017

93.2%#1/99 open

IndependentEpoch AI · Oct 2026

GLM 5.3 Flash

90.1%#10/99 open

IndependentEpoch AI · Aug 2026

AIME 2024/2025

DeepSeek V4.1 Flash 1017

99.4%#1/87 open

IndependentEpoch AI · Oct 2026

GLM 5.3 Flash

93.9%#10/87 open

IndependentEpoch AI · Aug 2026

FrontierMath

DeepSeek V4.1 Flash 1017

71.2%#2/18 open

IndependentEpoch AI · Oct 2026

GLM 5.3 Flash

55.8%#10/18 open

IndependentEpoch AI · Aug 2026

FrontierMath Tier 4

DeepSeek V4.1 Flash 1017

46.3%#1/14 open

IndependentEpoch AI · Oct 2026

GLM 5.3 Flash

17.1%#11/14 open

IndependentEpoch AI · Aug 2026

Chess Puzzles

DeepSeek V4.1 Flash 1017

46.0%#2/15 open

IndependentEpoch AI · Oct 2026

GLM 5.3 Flash

21.0%#10/15 open

IndependentEpoch AI · Aug 2026

LiveBench 2026 Coding

DeepSeek V4.1 Flash 1017

96.0#1/17 open

IndependentLiveBench · Oct 2026

GLM 5.3 Flash

80.6#7/17 open

IndependentLiveBench · Oct 2026

LiveBench 2026 Long-Horizon

DeepSeek V4.1 Flash 1017

50.9#1/17 open

IndependentLiveBench · Oct 2026

GLM 5.3 Flash

28.4#9/17 open

IndependentLiveBench · Oct 2026

LiveBench 2026 Reasoning

DeepSeek V4.1 Flash 1017

89.1#2/17 open

IndependentLiveBench · Oct 2026

GLM 5.3 Flash

77.6#11/17 open

IndependentLiveBench · Oct 2026

Mystery Game Puzzles

DeepSeek V4.1 Flash 1017

49.0%#1/19 open

IndependentEpoch AI · Oct 2026

GLM 5.3 Flash

8.0%#16/19 open

IndependentEpoch AI · Aug 2026

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

LMArena WebDev

DeepSeek V4.1 Flash 1017

1665.0#1/55 open

ArenaLMArena · Oct 2026

GLM 5.3 Flash

1607.7#9/55 open

ArenaLMArena · Oct 2026

LiveBench 2026 Browser

DeepSeek V4.1 Flash 1017

76.0#5/17 open

IndependentLiveBench · Oct 2026

GLM 5.3 Flash

84.0#4/17 open

IndependentLiveBench · Oct 2026

LiveBench 2026 Data Analysis

DeepSeek V4.1 Flash 1017

79.5#1/17 open

IndependentLiveBench · Oct 2026

GLM 5.3 Flash

76.4#6/17 open

IndependentLiveBench · Oct 2026

LiveBench 2026 Design

DeepSeek V4.1 Flash 1017

83.4#1/17 open

IndependentLiveBench · Oct 2026

GLM 5.3 Flash

77.2#6/17 open

IndependentLiveBench · Oct 2026

LiveBench 2026 Research

DeepSeek V4.1 Flash 1017

79.5#3/17 open

IndependentLiveBench · Oct 2026

GLM 5.3 Flash

70.1#10/17 open

IndependentLiveBench · Oct 2026

Only DeepSeek V4.1 Flash 1017 (1)

SimpleQA42.5%

Only GLM 5.3 Flash (17)

VRAM by quantization

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

QuantDeepSeek V4.1 Flash 1017GLM 5.3 Flash

Q2_K

DeepSeek V4.1 Flash 1017

325 GB264.5 GB file

32K 325 GB · 128K 326 GB

GLM 5.3 Flash

138 GB114.2 GB file

32K 161 GB · 128K 234 GB

Q3_K_M

DeepSeek V4.1 Flash 1017

372 GB347.3 GB file

32K 373 GB · 128K 374 GB

GLM 5.3 Flash

158 GB149.1 GB file

32K 181 GB · 128K 254 GB

Q4_K_M

DeepSeek V4.1 Flash 1017

458 GB444.7 GB file

32K 459 GB · 128K 460 GB

GLM 5.3 Flash

195 GB188.7 GB file

32K 217 GB · 128K 290 GB

Q5_K_M

DeepSeek V4.1 Flash 1017

544 GB~543.8 GB file

32K 545 GB · 128K 546 GB

GLM 5.3 Flash

231 GB~228.9 GB file

32K 253 GB · 128K 326 GB

Q6_K

DeepSeek V4.1 Flash 1017

630 GB~629.6 GB file

32K 630 GB · 128K 632 GB

GLM 5.3 Flash

267 GB~265.1 GB file

32K 290 GB · 128K 362 GB

Q8_0

DeepSeek V4.1 Flash 1017

764 GB~763.2 GB file

32K 764 GB · 128K 765 GB

GLM 5.3 Flash

323 GB341.0 GB file

32K 346 GB · 128K 418 GB

7 more quants

IQ2_XXS

DeepSeek V4.1 Flash 1017

210 GB300.5 GB file

32K 211 GB · 128K 212 GB

GLM 5.3 Flash

90.2 GB101.8 GB file

32K 113 GB · 128K 185 GB

IQ2_XS

DeepSeek V4.1 Flash 1017

229 GB~229.0 GB file

32K 230 GB · 128K 231 GB

GLM 5.3 Flash

not listed

IQ2_S

DeepSeek V4.1 Flash 1017

not listed

GLM 5.3 Flash

102 GB113.6 GB file

32K 125 GB · 128K 197 GB

IQ3_XXS

DeepSeek V4.1 Flash 1017

296 GB394.7 GB file

32K 296 GB · 128K 298 GB

GLM 5.3 Flash

126 GB120.4 GB file

32K 149 GB · 128K 221 GB

IQ3_S

DeepSeek V4.1 Flash 1017

325 GB423.6 GB file

32K 325 GB · 128K 326 GB

GLM 5.3 Flash

not listed

IQ4_XS

DeepSeek V4.1 Flash 1017

not listed

GLM 5.3 Flash

175 GB156.8 GB file

32K 197 GB · 128K 270 GB

BF16

DeepSeek V4.1 Flash 1017

1527 GB~1526.4 GB file

32K 1527 GB · 128K 1528 GB

GLM 5.3 Flash

644 GB641.6 GB file

32K 667 GB · 128K 740 GB

How to run each

DeepSeek V4.1 Flash 1017

Ollama · Q4_K_M

$ollama run hf.co/mrfakename/DeepSeek-V4.1-Flash-1017-GGUF:Q4_K_M

All ways to run DeepSeek V4.1 Flash 1017 →

GLM 5.3 Flash

Ollama · Q4_K_M

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

All ways to run GLM 5.3 Flash →

Specifications

Specifications of DeepSeek V4.1 Flash 1017 and GLM 5.3 Flash
Spec	DeepSeek V4.1 Flash 1017	GLM 5.3 Flash
Publisher	DeepSeek	Z.ai
Parameters	763.2B	321.3B
Active parameters	16B per token	18B per token
Architecture	DeepseekV41ForCausalLM	Glm5NextForConditionalGeneration
Context	1M tokens	1M tokens
Modalities	Vision	Vision, Function-calling
License	MIT	MIT
Released	Oct 2026	Aug 2026

Frequently Asked Questions

Which is better, DeepSeek V4.1 Flash 1017 or GLM 5.3 Flash?

DeepSeek V4.1 Flash 1017 leads llmrun Score 133.2 to 124.1; neither fits 24 GB. Choose DeepSeek V4.1 Flash 1017 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, DeepSeek V4.1 Flash 1017 or GLM 5.3 Flash?

At Q4_K_M, DeepSeek V4.1 Flash 1017 requires 458.3 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 DeepSeek V4.1 Flash 1017 or GLM 5.3 Flash on a 16 GB GPU?

DeepSeek V4.1 Flash 1017 does not fit (smallest quant needs 210.4 GB); GLM 5.3 Flash does not fit (smallest quant needs 100.7 GB).

Which has a longer context window, DeepSeek V4.1 Flash 1017 or GLM 5.3 Flash?

DeepSeek V4.1 Flash 1017 supports 1,048,576 tokens and GLM 5.3 Flash supports 1,048,576 tokens.