Llama 3.1 405B Instruct vs Mistral Large 3 675B Instruct 2512
Mistral Large 3 675B Instruct 2512 leads llmrun Score 89.6 to 83.2 (ranges overlap); neither fits 24 GB.
Model A · Meta
Llama 3.1 405B Instruct405.9B · Llama 3.1 Community · Jul 2024
Model B · Mistral AI
Mistral Large 3 675B Instruct 2512675B · Apache 2.0 · Nov 2025
Choose Llama 3.1 405B Instruct if you want…
Lighter on memory
267.9 vs 445.5 GB at Q4_K_M
Choose Mistral Large 3 675B Instruct 2512 if you want…
Higher llmrun Score
89.6 vs 83.2, ranges overlap
More permissive license
Apache 2.0 vs Llama 3.1 Community
Newer release
Nov 2025 vs Jul 2024
On your hardware
Each model at its default quant (Q4_K_M), a smaller one when it must. Estimates, ±20%.
8 GB
RTX 4060 · 8 GB tier
Llama 3.1 405B Instruct
Doesn't fit
smallest quant needs 197.4 GB
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
12 GB
RTX 3060 12GB · 12 GB tier
Llama 3.1 405B Instruct
Doesn't fit
smallest quant needs 197.4 GB
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Llama 3.1 405B Instruct
Doesn't fit
smallest quant needs 197.4 GB
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
24 GBreference
RTX 4090 · 24 GB tier
Llama 3.1 405B Instruct
Doesn't fit
smallest quant needs 197.4 GB
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
32 GB
RTX 5090 · 32 GB tier
Llama 3.1 405B Instruct
Doesn't fit
smallest quant needs 197.4 GB
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
48 GB
RTX A6000 · 48 GB tier
Llama 3.1 405B Instruct
Doesn't fit
smallest quant needs 197.4 GB
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
Mac 32 GB
Mac Mini M4 · Macs
Llama 3.1 405B Instruct
Doesn't fit
smallest quant needs 197.4 GB
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
Mac 64 GB
Mac Studio M4 Max · Macs
Llama 3.1 405B Instruct
Doesn't fit
smallest quant needs 197.4 GB
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
Mac 128 GB
Mac Studio M4 Max · Macs
Llama 3.1 405B Instruct
Doesn't fit
smallest quant needs 197.4 GB
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
Llama 3.1 405B Instruct
Mistral Large 3 675B Instruct 2512
Coding
Llama 3.1 405B Instruct
no data
Mistral Large 3 675B Instruct 2512
Science
Llama 3.1 405B Instruct
no data
Mistral Large 3 675B Instruct 2512
Reasoning
Llama 3.1 405B Instruct
Mistral Large 3 675B Instruct 2512
Llama 3.1 405B Instruct · #76 of 100 open models · #73 of 96 that fit ≤512 GB
Mistral Large 3 675B Instruct 2512 · #69 of 100 open models · #66 of 96 that fit ≤512 GB
Benchmarks
1 shared board: Llama 3.1 405B Instruct leads 0, Mistral Large 3 675B Instruct 2512 leads 1 · Benchmarks imported Oct 2026
Llama 3.1 405B Instruct
61.4%#42/68 open
Lab-reportedEpoch AI · Jul 2024
Mistral Large 3 675B Instruct 2512
65.1%#37/68 open
Lab-reportedEpoch AI · Dec 2025
15 more boards (other shared and single-model boards)
Llama 3.1 405B Instruct
1335.5#86/187 open
ArenaLMArena · Oct 2026
Mistral Large 3 675B Instruct 2512
1414.2#41/187 open
ArenaLMArena · Oct 2026
Only Llama 3.1 405B Instruct (9)
- GPQA Diamond50.9%
- AIME 2024/20259.7%
- MMLU-Pro73.3%
- SimpleBench23.0%
- MATH Level 549.8%
- MMLU84.5%
- WeirdML21.4%
- ForecastBench59.9
- WinoGrande82.2%
Only Mistral Large 3 675B Instruct 2512 (5)
- LMArena WebDev1230.5
- SciCode36.6%
- CritPt0.0%
- LMCA16.7%
- ALE-Bench264.7
VRAM by quantization
Memory to load the model and 2K context; below it, the total at 32K and 128K context. Lighter side in bold.
Q2_K
Llama 3.1 405B Instruct
190 GB151.2 GB file
32K 206 GB · 128K 259 GB
Mistral Large 3 675B Instruct 2512
316 GB247.1 GB file
32K 335 GB · 128K 396 GB
Q3_K_S
Llama 3.1 405B Instruct
195 GB177.1 GB file
32K 212 GB · 128K 265 GB
Mistral Large 3 675B Instruct 2512
325 GB291.9 GB file
32K 344 GB · 128K 405 GB
Q3_K_M
Llama 3.1 405B Instruct
218 GB~197.8 GB file
32K 234 GB · 128K 287 GB
Mistral Large 3 675B Instruct 2512
362 GB321.8 GB file
32K 381 GB · 128K 442 GB
Q4_0
Llama 3.1 405B Instruct
not listed
Mistral Large 3 675B Instruct 2512
371 GB381.7 GB file
32K 390 GB · 128K 451 GB
Q4_K_M
Llama 3.1 405B Instruct
268 GB~243.5 GB file
32K 284 GB · 128K 337 GB
Mistral Large 3 675B Instruct 2512
446 GB407.0 GB file
32K 465 GB · 128K 525 GB
Q5_K_M
Llama 3.1 405B Instruct
318 GB~289.2 GB file
32K 335 GB · 128K 387 GB
Mistral Large 3 675B Instruct 2512
529 GB478.0 GB file
32K 548 GB · 128K 609 GB
Q6_K
Llama 3.1 405B Instruct
368 GB~334.8 GB file
32K 385 GB · 128K 438 GB
Mistral Large 3 675B Instruct 2512
613 GB553.3 GB file
32K 632 GB · 128K 693 GB
Q8_0
Llama 3.1 405B Instruct
446 GB~405.9 GB file
32K 463 GB · 128K 516 GB
Mistral Large 3 675B Instruct 2512
743 GB715.7 GB file
32K 762 GB · 128K 822 GB
14 more quants
IQ2_XXS
Llama 3.1 405B Instruct
not listed
Mistral Large 3 675B Instruct 2512
204 GB224.8 GB file
32K 223 GB · 128K 284 GB
IQ2_XS
Llama 3.1 405B Instruct
not listed
Mistral Large 3 675B Instruct 2512
223 GB189.5 GB file
32K 242 GB · 128K 303 GB
IQ2_S
Llama 3.1 405B Instruct
not listed
Mistral Large 3 675B Instruct 2512
232 GB190.8 GB file
32K 251 GB · 128K 312 GB
IQ2_M
Llama 3.1 405B Instruct
not listed
Mistral Large 3 675B Instruct 2512
251 GB235.4 GB file
32K 270 GB · 128K 331 GB
IQ3_XXS
Llama 3.1 405B Instruct
not listed
Mistral Large 3 675B Instruct 2512
288 GB279.2 GB file
32K 307 GB · 128K 368 GB
IQ3_XS
Llama 3.1 405B Instruct
not listed
Mistral Large 3 675B Instruct 2512
306 GB279.1 GB file
32K 325 GB · 128K 386 GB
IQ3_M
Llama 3.1 405B Instruct
not listed
Mistral Large 3 675B Instruct 2512
334 GB309.9 GB file
32K 353 GB · 128K 414 GB
Q3_K_L
Llama 3.1 405B Instruct
not listed
Mistral Large 3 675B Instruct 2512
381 GB321.7 GB file
32K 400 GB · 128K 460 GB
IQ4_XS
Llama 3.1 405B Instruct
not listed
Mistral Large 3 675B Instruct 2512
399 GB360.0 GB file
32K 418 GB · 128K 479 GB
IQ4_NL
Llama 3.1 405B Instruct
not listed
Mistral Large 3 675B Instruct 2512
418 GB380.7 GB file
32K 437 GB · 128K 498 GB
Q4_1
Llama 3.1 405B Instruct
not listed
Mistral Large 3 675B Instruct 2512
418 GB422.4 GB file
32K 437 GB · 128K 498 GB
Q4_K_S
Llama 3.1 405B Instruct
not listed
Mistral Large 3 675B Instruct 2512
418 GB382.7 GB file
32K 437 GB · 128K 498 GB
Q5_K_S
Llama 3.1 405B Instruct
not listed
Mistral Large 3 675B Instruct 2512
510 GB464.4 GB file
32K 530 GB · 128K 590 GB
BF16
Llama 3.1 405B Instruct
893 GB~811.7 GB file
32K 909 GB · 128K 962 GB
Mistral Large 3 675B Instruct 2512
1485 GB1347.0 GB file
32K 1504 GB · 128K 1565 GB
Llama 3.1 405B Instruct
Ollama · Q4_K_M
ollama run hf.co/MaziyarPanahi/Meta-Llama-3.1-405B-Instruct-GGUFMistral Large 3 675B Instruct 2512
Ollama · Q4_K_M
ollama run hf.co/unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:Q4_K_M| Spec | Llama 3.1 405B Instruct | Mistral Large 3 675B Instruct 2512 |
|---|---|---|
| Publisher | Meta | Mistral AI |
| Parameters | 405.9B | 675B |
| Modalities | Chat, Function-calling | Chat, Function-calling |
| License | Llama 3.1 Community | Apache 2.0 |
| Released | Jul 2024 | Nov 2025 |
Frequently Asked Questions
Which is better, Llama 3.1 405B Instruct or Mistral Large 3 675B Instruct 2512?
Mistral Large 3 675B Instruct 2512 leads llmrun Score 89.6 to 83.2 (ranges overlap); neither fits 24 GB. Choose Llama 3.1 405B Instruct for lighter on memory; choose Mistral Large 3 675B Instruct 2512 for higher llmrun Score and more permissive license.
Which needs less VRAM, Llama 3.1 405B Instruct or Mistral Large 3 675B Instruct 2512?
At Q4_K_M, Llama 3.1 405B Instruct requires 267.9 GB while Mistral Large 3 675B Instruct 2512 needs 445.5 GB, making Llama 3.1 405B Instruct the easier model to run on your local setup.
Can I run Llama 3.1 405B Instruct or Mistral Large 3 675B Instruct 2512 on a 16 GB GPU?
Llama 3.1 405B Instruct does not fit (smallest quant needs 197.4 GB); Mistral Large 3 675B Instruct 2512 does not fit (smallest quant needs 213.1 GB).