Llama 3.1 405B Instruct vs Llama 4 Maverick 17B 128E Instruct

Llama 4 Maverick 17B 128E Instruct leads llmrun Score 87.1 to 83.2 (ranges overlap); neither fits 24 GB.

Model A · Meta

Llama 3.1 405B Instruct

83.2llmrun Score

405.9B · Llama 3.1 Community · Jul 2024

ChatFunctions

Model B · Meta

Llama 4 Maverick 17B 128E Instruct

87.1llmrun Score

401.6B · 17B active · Other · Apr 2025

Vision

Which should you choose?

Choose Llama 3.1 405B Instruct if you want…

Also does chat, function-calling
Llama 4 Maverick 17B 128E Instruct doesn't list it

Choose Llama 4 Maverick 17B 128E Instruct if you want…

Higher llmrun Score
87.1 vs 83.2, ranges overlap
Ahead on the benchmarks
7 of 8 shared boards
Also does vision
Llama 3.1 405B Instruct doesn't list it
Newer release
Apr 2025 vs Jul 2024

On your hardware

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

MemoryLlama 3.1 405B InstructLlama 4 Maverick 17B 128E Instruct

8 GB

RTX 4060 · 8 GB tier

Llama 3.1 405B Instruct

Doesn't fit

smallest quant needs 197.4 GB

Llama 4 Maverick 17B 128E Instruct

Doesn't fit

smallest quant needs 129.2 GB

12 GB

RTX 3060 12GB · 12 GB tier

Llama 3.1 405B Instruct

Doesn't fit

smallest quant needs 197.4 GB

Llama 4 Maverick 17B 128E Instruct

Doesn't fit

smallest quant needs 129.2 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Llama 3.1 405B Instruct

Doesn't fit

smallest quant needs 197.4 GB

Llama 4 Maverick 17B 128E Instruct

Doesn't fit

smallest quant needs 129.2 GB

24 GBreference

RTX 4090 · 24 GB tier

Llama 3.1 405B Instruct

Doesn't fit

smallest quant needs 197.4 GB

Llama 4 Maverick 17B 128E Instruct

Doesn't fit

smallest quant needs 129.2 GB

32 GB

RTX 5090 · 32 GB tier

Llama 3.1 405B Instruct

Doesn't fit

smallest quant needs 197.4 GB

Llama 4 Maverick 17B 128E Instruct

Doesn't fit

smallest quant needs 129.2 GB

48 GB

RTX A6000 · 48 GB tier

Llama 3.1 405B Instruct

Doesn't fit

smallest quant needs 197.4 GB

Llama 4 Maverick 17B 128E Instruct

Doesn't fit

smallest quant needs 129.2 GB

Mac 32 GB

Mac Mini M4 · Macs

Llama 3.1 405B Instruct

Doesn't fit

smallest quant needs 197.4 GB

Llama 4 Maverick 17B 128E Instruct

Doesn't fit

smallest quant needs 129.2 GB

Mac 64 GB

Mac Studio M4 Max · Macs

Llama 3.1 405B Instruct

Doesn't fit

smallest quant needs 197.4 GB

Llama 4 Maverick 17B 128E Instruct

Doesn't fit

smallest quant needs 129.2 GB

Mac 128 GB

Mac Studio M4 Max · Macs

Llama 3.1 405B Instruct

Doesn't fit

smallest quant needs 197.4 GB

Llama 4 Maverick 17B 128E Instruct

Doesn't fit

smallest quant needs 129.2 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

Llama 3.1 405B Instruct Llama 4 Maverick 17B 128E Instruct

Overall

Llama 3.1 405B Instruct

83.279–87

Llama 4 Maverick 17B 128E Instruct

87.184–90

Coding

Llama 3.1 405B Instruct

no data

Llama 4 Maverick 17B 128E Instruct

81.174–89

Science

Llama 3.1 405B Instruct

no data

Llama 4 Maverick 17B 128E Instruct

95.989–103

Reasoning

Llama 3.1 405B Instruct

85.077–93

Llama 4 Maverick 17B 128E Instruct

85.278–93

Llama 3.1 405B Instruct · #76 of 100 open models · #73 of 96 that fit ≤512 GB

Llama 4 Maverick 17B 128E Instruct · #72 of 100 open models · #69 of 96 that fit ≤512 GB

Benchmarks

8 shared boards: Llama 3.1 405B Instruct leads 1, Llama 4 Maverick 17B 128E Instruct leads 7 · Benchmarks imported Oct 2026

BoardLlama 3.1 405B InstructLlama 4 Maverick 17B 128E Instruct

GPQA Diamond

Llama 3.1 405B Instruct

50.9%#53/98 open

IndependentEpoch AI · Jul 2024

Llama 4 Maverick 17B 128E Instruct

67.0%#36/98 open

IndependentEpoch AI · Apr 2025

AIME 2024/2025

Llama 3.1 405B Instruct

9.7%#58/86 open

IndependentEpoch AI · Jul 2024

Llama 4 Maverick 17B 128E Instruct

20.6%#54/86 open

IndependentEpoch AI · Apr 2025

MMLU-Pro

Llama 3.1 405B Instruct

73.3%#34/145 open

IndependentTIGER-Lab

Llama 4 Maverick 17B 128E Instruct

80.5%#24/145 open

IndependentTIGER-Lab

SimpleBench

Llama 3.1 405B Instruct

23.0%#20/25 open

IndependentEpoch AI · Jul 2024

Llama 4 Maverick 17B 128E Instruct

27.7%#17/25 open

IndependentEpoch AI · Apr 2025

MATH Level 5

Llama 3.1 405B Instruct

49.8%#15/39 open

IndependentEpoch AI · Jul 2024

Llama 4 Maverick 17B 128E Instruct

73.0%#7/39 open

IndependentEpoch AI · Apr 2025

WeirdML

Llama 3.1 405B Instruct

21.4%#40/46 open

IndependentEpoch AI · Jul 2024

Llama 4 Maverick 17B 128E Instruct

24.5%#39/46 open

IndependentEpoch AI · Apr 2025

DTBench

Llama 3.1 405B Instruct

61.4%#42/68 open

Lab-reportedEpoch AI · Jul 2024

Llama 4 Maverick 17B 128E Instruct

61.9%#41/68 open

Lab-reportedEpoch AI · Apr 2025

ForecastBench

Llama 3.1 405B Instruct

59.9#6/26 open

Lab-reportedEpoch AI · Jul 2024

Llama 4 Maverick 17B 128E Instruct

57.5#16/26 open

Lab-reportedEpoch AI · Apr 2025

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

LMArena Text

Llama 3.1 405B Instruct

1335.5#86/187 open

ArenaLMArena · Oct 2026

Llama 4 Maverick 17B 128E Instruct

1327.0#89/187 open

ArenaLMArena · Oct 2026

Only Llama 3.1 405B Instruct (2)

MMLU84.5%
WinoGrande82.2%

Only Llama 4 Maverick 17B 128E Instruct (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.

QuantLlama 3.1 405B InstructLlama 4 Maverick 17B 128E Instruct

Q2_K

Llama 3.1 405B Instruct

190 GB151.2 GB file

32K 206 GB · 128K 259 GB

Llama 4 Maverick 17B 128E Instruct

188 GB145.6 GB file

32K 204 GB · 128K 257 GB

Q3_K_S

Llama 3.1 405B Instruct

195 GB177.1 GB file

32K 212 GB · 128K 265 GB

Llama 4 Maverick 17B 128E Instruct

193 GB172.7 GB file

32K 210 GB · 128K 262 GB

Q3_K_M

Llama 3.1 405B Instruct

218 GB~197.8 GB file

32K 234 GB · 128K 287 GB

Llama 4 Maverick 17B 128E Instruct

215 GB191.1 GB file

32K 232 GB · 128K 284 GB

Q4_0

Llama 3.1 405B Instruct

not listed

Llama 4 Maverick 17B 128E Instruct

221 GB226.8 GB file

32K 237 GB · 128K 290 GB

Q4_K_M

Llama 3.1 405B Instruct

268 GB~243.5 GB file

32K 284 GB · 128K 337 GB

Llama 4 Maverick 17B 128E Instruct

265 GB242.8 GB file

32K 282 GB · 128K 334 GB

Q5_K_M

Llama 3.1 405B Instruct

318 GB~289.2 GB file

32K 335 GB · 128K 387 GB

Llama 4 Maverick 17B 128E Instruct

315 GB284.5 GB file

32K 331 GB · 128K 384 GB

Q6_K

Llama 3.1 405B Instruct

368 GB~334.8 GB file

32K 385 GB · 128K 438 GB

Llama 4 Maverick 17B 128E Instruct

364 GB328.8 GB file

32K 381 GB · 128K 434 GB

Q8_0

Llama 3.1 405B Instruct

446 GB~405.9 GB file

32K 463 GB · 128K 516 GB

Llama 4 Maverick 17B 128E Instruct

442 GB425.8 GB file

32K 458 GB · 128K 511 GB

9 more quants

IQ2_XXS

Llama 3.1 405B Instruct

not listed

Llama 4 Maverick 17B 128E Instruct

121 GB135.2 GB file

32K 138 GB · 128K 191 GB

IQ2_M

Llama 3.1 405B Instruct

not listed

Llama 4 Maverick 17B 128E Instruct

149 GB141.2 GB file

32K 166 GB · 128K 218 GB

IQ3_XXS

Llama 3.1 405B Instruct

not listed

Llama 4 Maverick 17B 128E Instruct

171 GB169.3 GB file

32K 188 GB · 128K 240 GB

IQ4_XS

Llama 3.1 405B Instruct

not listed

Llama 4 Maverick 17B 128E Instruct

237 GB214.3 GB file

32K 254 GB · 128K 307 GB

IQ4_NL

Llama 3.1 405B Instruct

not listed

Llama 4 Maverick 17B 128E Instruct

248 GB225.8 GB file

32K 265 GB · 128K 318 GB

Q4_1

Llama 3.1 405B Instruct

not listed

Llama 4 Maverick 17B 128E Instruct

248 GB250.7 GB file

32K 265 GB · 128K 318 GB

Q4_K_S

Llama 3.1 405B Instruct

not listed

Llama 4 Maverick 17B 128E Instruct

248 GB227.8 GB file

32K 265 GB · 128K 318 GB

Q5_K_S

Llama 3.1 405B Instruct

not listed

Llama 4 Maverick 17B 128E Instruct

304 GB275.7 GB file

32K 320 GB · 128K 373 GB

BF16

Llama 3.1 405B Instruct

893 GB~811.7 GB file

32K 909 GB · 128K 962 GB

Llama 4 Maverick 17B 128E Instruct

883 GB801.5 GB file

32K 900 GB · 128K 953 GB

How to run each

Llama 3.1 405B Instruct

Ollama · Q4_K_M

$ollama run hf.co/MaziyarPanahi/Meta-Llama-3.1-405B-Instruct-GGUF

All ways to run Llama 3.1 405B Instruct →

Llama 4 Maverick 17B 128E Instruct

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF:Q4_K_M

All ways to run Llama 4 Maverick 17B 128E Instruct →

Specifications

Specifications of Llama 3.1 405B Instruct and Llama 4 Maverick 17B 128E Instruct
Spec	Llama 3.1 405B Instruct	Llama 4 Maverick 17B 128E Instruct
Publisher	Meta	Meta
Parameters	405.9B	401.6B
Active parameters	—	17B per token
Modalities	Chat, Function-calling	Vision
License	Llama 3.1 Community	Other
Released	Jul 2024	Apr 2025

Frequently Asked Questions

Which is better, Llama 3.1 405B Instruct or Llama 4 Maverick 17B 128E Instruct?

Llama 4 Maverick 17B 128E Instruct leads llmrun Score 87.1 to 83.2 (ranges overlap); neither fits 24 GB. Choose Llama 3.1 405B Instruct for also does chat, function-calling; choose Llama 4 Maverick 17B 128E Instruct for higher llmrun Score and ahead on the benchmarks.

Which needs less VRAM, Llama 3.1 405B Instruct or Llama 4 Maverick 17B 128E Instruct?

At Q4_K_M, Llama 3.1 405B Instruct requires 267.9 GB while Llama 4 Maverick 17B 128E Instruct needs 265.1 GB, making Llama 4 Maverick 17B 128E Instruct the easier model to run on your local setup.

Can I run Llama 3.1 405B Instruct or Llama 4 Maverick 17B 128E Instruct on a 16 GB GPU?

Llama 3.1 405B Instruct does not fit (smallest quant needs 197.4 GB); Llama 4 Maverick 17B 128E Instruct does not fit (smallest quant needs 129.2 GB).