DeepSeek v3 0324 vs Mistral Large 3 675B Instruct 2512
DeepSeek v3 0324 leads llmrun Score 93.9 to 89.6 (ranges overlap); neither fits 24 GB.
Model A · DeepSeek
DeepSeek v3 0324684.5B · 40.1B active · 160K context · MIT · Mar 2025
Model B · Mistral AI
Mistral Large 3 675B Instruct 2512675B · Apache 2.0 · Nov 2025
Choose DeepSeek v3 0324 if you want…
Higher llmrun Score
93.9 vs 89.6, ranges overlap
Stronger at coding
99.5 vs 92.7
Choose Mistral Large 3 675B Instruct 2512 if you want…
Newer release
Nov 2025 vs Mar 2025
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
DeepSeek v3 0324
Doesn't fit
smallest quant needs 189.7 GB
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
12 GB
RTX 3060 12GB · 12 GB tier
DeepSeek v3 0324
Doesn't fit
smallest quant needs 189.7 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
DeepSeek v3 0324
Doesn't fit
smallest quant needs 189.7 GB
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
24 GBreference
RTX 4090 · 24 GB tier
DeepSeek v3 0324
Doesn't fit
smallest quant needs 189.7 GB
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
32 GB
RTX 5090 · 32 GB tier
DeepSeek v3 0324
Doesn't fit
smallest quant needs 189.7 GB
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
48 GB
RTX A6000 · 48 GB tier
DeepSeek v3 0324
Doesn't fit
smallest quant needs 189.7 GB
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
Mac 32 GB
Mac Mini M4 · Macs
DeepSeek v3 0324
Doesn't fit
smallest quant needs 189.7 GB
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
Mac 64 GB
Mac Studio M4 Max · Macs
DeepSeek v3 0324
Doesn't fit
smallest quant needs 189.7 GB
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
Mac 128 GB
Mac Studio M4 Max · Macs
DeepSeek v3 0324
Doesn't fit
smallest quant needs 189.7 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
DeepSeek v3 0324
Mistral Large 3 675B Instruct 2512
Coding
DeepSeek v3 0324
Mistral Large 3 675B Instruct 2512
Science
DeepSeek v3 0324
Mistral Large 3 675B Instruct 2512
Reasoning
DeepSeek v3 0324
Mistral Large 3 675B Instruct 2512
DeepSeek v3 0324 · #66 of 100 open models · #63 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
4 shared boards: DeepSeek v3 0324 leads 1, Mistral Large 3 675B Instruct 2512 leads 1 · Benchmarks imported Oct 2026
DeepSeek v3 0324
39.0%#32/66 open
Lab-reportedEpoch AI · Mar 2025
Mistral Large 3 675B Instruct 2512
36.6%#39/66 open
Lab-reportedEpoch AI · Dec 2025
DeepSeek v3 0324
0.0%#48/66 open
Lab-reportedEpoch AI · Mar 2025
Mistral Large 3 675B Instruct 2512
0.0%#59/66 open
Lab-reportedEpoch AI · Dec 2025
DeepSeek v3 0324
64.8%#38/68 open
Lab-reportedEpoch AI · Mar 2025
Mistral Large 3 675B Instruct 2512
65.1%#37/68 open
Lab-reportedEpoch AI · Dec 2025
DeepSeek v3 0324
15.5%#41/54 open
Lab-reportedEpoch AI · Mar 2025
Mistral Large 3 675B Instruct 2512
16.7%#38/54 open
Lab-reportedEpoch AI · Dec 2025
13 more boards (other shared and single-model boards)
DeepSeek v3 0324
1395.2#52/187 open
ArenaLMArena · Oct 2026
Mistral Large 3 675B Instruct 2512
1414.2#41/187 open
ArenaLMArena · Oct 2026
Only DeepSeek v3 0324 (10)
- SWE-bench Verified42.0%
- GPQA Diamond67.6%
- AIME 2024/202537.8%
- MMLU-Pro81.3%
- Aider Polyglot55.1%
- SimpleBench27.2%
- MATH Level 575.5%
- WeirdML36.1%
- Fiction.LiveBench50.0%
- METR Time Horizons49.6%
Only Mistral Large 3 675B Instruct 2512 (2)
- LMArena WebDev1230.5
- 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
DeepSeek v3 0324
295 GB244.0 GB file
32K 294 GB · 128K 300 GB
Mistral Large 3 675B Instruct 2512
316 GB247.1 GB file
32K 335 GB · 128K 396 GB
Q3_K_S
DeepSeek v3 0324
303 GB289.1 GB file
32K 302 GB · 128K 309 GB
Mistral Large 3 675B Instruct 2512
325 GB291.9 GB file
32K 344 GB · 128K 405 GB
Q3_K_M
DeepSeek v3 0324
338 GB319.2 GB file
32K 336 GB · 128K 343 GB
Mistral Large 3 675B Instruct 2512
362 GB321.8 GB file
32K 381 GB · 128K 442 GB
Q4_0
DeepSeek v3 0324
346 GB379.0 GB file
32K 345 GB · 128K 352 GB
Mistral Large 3 675B Instruct 2512
371 GB381.7 GB file
32K 390 GB · 128K 451 GB
Q4_K_M
DeepSeek v3 0324
415 GB404.4 GB file
32K 413 GB · 128K 420 GB
Mistral Large 3 675B Instruct 2512
446 GB407.0 GB file
32K 465 GB · 128K 525 GB
Q5_K_M
DeepSeek v3 0324
492 GB475.4 GB file
32K 490 GB · 128K 497 GB
Mistral Large 3 675B Instruct 2512
529 GB478.0 GB file
32K 548 GB · 128K 609 GB
Q6_K
DeepSeek v3 0324
569 GB550.8 GB file
32K 567 GB · 128K 574 GB
Mistral Large 3 675B Instruct 2512
613 GB553.3 GB file
32K 632 GB · 128K 693 GB
Q8_0
DeepSeek v3 0324
688 GB713.3 GB file
32K 687 GB · 128K 694 GB
Mistral Large 3 675B Instruct 2512
743 GB715.7 GB file
32K 762 GB · 128K 822 GB
14 more quants
IQ2_XXS
DeepSeek v3 0324
192 GB218.7 GB file
32K 191 GB · 128K 198 GB
Mistral Large 3 675B Instruct 2512
204 GB224.8 GB file
32K 223 GB · 128K 284 GB
IQ2_XS
DeepSeek v3 0324
not listed
Mistral Large 3 675B Instruct 2512
223 GB189.5 GB file
32K 242 GB · 128K 303 GB
IQ2_S
DeepSeek v3 0324
218 GB197.0 GB file
32K 217 GB · 128K 223 GB
Mistral Large 3 675B Instruct 2512
232 GB190.8 GB file
32K 251 GB · 128K 312 GB
IQ2_M
DeepSeek v3 0324
235 GB217.4 GB file
32K 234 GB · 128K 241 GB
Mistral Large 3 675B Instruct 2512
251 GB235.4 GB file
32K 270 GB · 128K 331 GB
IQ3_XXS
DeepSeek v3 0324
269 GB257.9 GB file
32K 268 GB · 128K 275 GB
Mistral Large 3 675B Instruct 2512
288 GB279.2 GB file
32K 307 GB · 128K 368 GB
IQ3_XS
DeepSeek v3 0324
not listed
Mistral Large 3 675B Instruct 2512
306 GB279.1 GB file
32K 325 GB · 128K 386 GB
IQ3_M
DeepSeek v3 0324
not listed
Mistral Large 3 675B Instruct 2512
334 GB309.9 GB file
32K 353 GB · 128K 414 GB
Q3_K_L
DeepSeek v3 0324
355 GB347.4 GB file
32K 353 GB · 128K 360 GB
Mistral Large 3 675B Instruct 2512
381 GB321.7 GB file
32K 400 GB · 128K 460 GB
IQ4_XS
DeepSeek v3 0324
372 GB357.1 GB file
32K 371 GB · 128K 377 GB
Mistral Large 3 675B Instruct 2512
399 GB360.0 GB file
32K 418 GB · 128K 479 GB
IQ4_NL
DeepSeek v3 0324
389 GB378.1 GB file
32K 388 GB · 128K 395 GB
Mistral Large 3 675B Instruct 2512
418 GB380.7 GB file
32K 437 GB · 128K 498 GB
Q4_1
DeepSeek v3 0324
389 GB419.9 GB file
32K 388 GB · 128K 395 GB
Mistral Large 3 675B Instruct 2512
418 GB422.4 GB file
32K 437 GB · 128K 498 GB
Q4_K_S
DeepSeek v3 0324
389 GB380.0 GB file
32K 388 GB · 128K 395 GB
Mistral Large 3 675B Instruct 2512
418 GB382.7 GB file
32K 437 GB · 128K 498 GB
Q5_K_S
DeepSeek v3 0324
475 GB461.8 GB file
32K 473 GB · 128K 480 GB
Mistral Large 3 675B Instruct 2512
510 GB464.4 GB file
32K 530 GB · 128K 590 GB
BF16
DeepSeek v3 0324
1373 GB1342.3 GB file
32K 1372 GB · 128K 1379 GB
Mistral Large 3 675B Instruct 2512
1485 GB1347.0 GB file
32K 1504 GB · 128K 1565 GB
DeepSeek v3 0324
Ollama · Q4_K_M
ollama run hf.co/unsloth/DeepSeek-V3-0324-GGUF:Q4_K_MMistral 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 | DeepSeek v3 0324 | Mistral Large 3 675B Instruct 2512 |
|---|---|---|
| Publisher | DeepSeek | Mistral AI |
| Parameters | 684.5B | 675B |
| Active parameters | 40B per token | — |
| Architecture | DeepseekV3ForCausalLM | — |
| Context | 160K tokens | — |
| Modalities | Chat, Function-calling | Chat, Function-calling |
| License | MIT | Apache 2.0 |
| Released | Mar 2025 | Nov 2025 |
Frequently Asked Questions
Which is better, DeepSeek v3 0324 or Mistral Large 3 675B Instruct 2512?
DeepSeek v3 0324 leads llmrun Score 93.9 to 89.6 (ranges overlap); neither fits 24 GB. Choose DeepSeek v3 0324 for higher llmrun Score and stronger at coding; choose Mistral Large 3 675B Instruct 2512 for newer release.
Which needs less VRAM, DeepSeek v3 0324 or Mistral Large 3 675B Instruct 2512?
At Q4_K_M, DeepSeek v3 0324 requires 414.6 GB while Mistral Large 3 675B Instruct 2512 needs 445.5 GB, making DeepSeek v3 0324 the easier model to run on your local setup.
Can I run DeepSeek v3 0324 or Mistral Large 3 675B Instruct 2512 on a 16 GB GPU?
DeepSeek v3 0324 does not fit (smallest quant needs 189.7 GB); Mistral Large 3 675B Instruct 2512 does not fit (smallest quant needs 213.1 GB).