Mistral Large 3 675B Instruct 2512 vs GLM 5.3 Flash
GLM 5.3 Flash leads llmrun Score 124.1 to 89.6; neither fits 24 GB.
Run GLM 5.3 Flash in the cloud →
Model A · Mistral AI
Mistral Large 3 675B Instruct 2512675B · 41B active · Apache 2.0 · Nov 2025
Model B · Z.ai
GLM 5.3 Flash321.3B · 18.3B active · 1M context · MIT · Aug 2026
Choose Mistral Large 3 675B Instruct 2512 if you want…
Also does chat
GLM 5.3 Flash doesn't list it
Choose GLM 5.3 Flash if you want…
Higher llmrun Score
124.1 vs 89.6
Stronger at reasoning
127.4 vs 89.0
Stronger at science
123.5 vs 96.9
Ahead on the benchmarks
3 of 3 shared boards
Lighter on memory
194.6 vs 445.5 GB at Q4_K_M
Also does vision
Mistral Large 3 675B Instruct 2512 doesn't list it
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
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
GLM 5.3 Flash
Doesn't fit
smallest quant needs 100.7 GB
12 GB
RTX 3060 12GB · 12 GB tier
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
GLM 5.3 Flash
Doesn't fit
smallest quant needs 100.7 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
GLM 5.3 Flash
Doesn't fit
smallest quant needs 100.7 GB
24 GBreference
RTX 4090 · 24 GB tier
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
GLM 5.3 Flash
Doesn't fit
smallest quant needs 100.7 GB
32 GB
RTX 5090 · 32 GB tier
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
GLM 5.3 Flash
Doesn't fit
smallest quant needs 100.7 GB
48 GB
RTX A6000 · 48 GB tier
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
GLM 5.3 Flash
Doesn't fit
smallest quant needs 100.7 GB
Mac 32 GB
Mac Mini M4 · Macs
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
GLM 5.3 Flash
Doesn't fit
smallest quant needs 100.7 GB
Mac 64 GB
Mac Studio M4 Max · Macs
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 GB
GLM 5.3 Flash
Doesn't fit
smallest quant needs 100.7 GB
Mac 128 GB
Mac Studio M4 Max · Macs
Mistral Large 3 675B Instruct 2512
Doesn't fit
smallest quant needs 213.1 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).
Overall
Mistral Large 3 675B Instruct 2512
GLM 5.3 Flash
Coding
Mistral Large 3 675B Instruct 2512
GLM 5.3 Flash
Agents
Mistral Large 3 675B Instruct 2512
no data
GLM 5.3 Flash
Math
Mistral Large 3 675B Instruct 2512
no data
GLM 5.3 Flash
Science
Mistral Large 3 675B Instruct 2512
GLM 5.3 Flash
Reasoning
Mistral Large 3 675B Instruct 2512
GLM 5.3 Flash
Mistral Large 3 675B Instruct 2512 · #75 of 106 open models · #71 of 102 that fit ≤512 GB
GLM 5.3 Flash · #12 of 106 open models · #6 of 89 that fit ≤256 GB
Benchmarks
3 shared boards: Mistral Large 3 675B Instruct 2512 leads 0, GLM 5.3 Flash leads 3 · Benchmarks imported Nov 2026
Mistral Large 3 675B Instruct 2512
36.6%#47/72 open
Lab-reportedEpoch AI · Dec 2025
GLM 5.3 Flash
51.6%#11/72 open
Lab-reportedEpoch AI · Aug 2026
Mistral Large 3 675B Instruct 2512
264.7#46/48 open
Lab-reportedEpoch AI · Dec 2025
GLM 5.3 Flash
303.6#44/48 open
Lab-reportedEpoch AI · Aug 2026
Mistral Large 3 675B Instruct 2512
0.0%#72/84 open
Lab-reportedEpoch AI · Dec 2025
GLM 5.3 Flash
15.4%#10/84 open
Lab-reportedEpoch AI · Aug 2026
30 more boards (other shared and single-model boards)
Mistral Large 3 675B Instruct 2512
1414.3#41/188 open
ArenaLMArena · Oct 2026
GLM 5.3 Flash
1476.5#4/188 open
ArenaLMArena · Oct 2026
Mistral Large 3 675B Instruct 2512
1232.6#53/55 open
ArenaLMArena · Oct 2026
GLM 5.3 Flash
1606.6#9/55 open
ArenaLMArena · Oct 2026
Only GLM 5.3 Flash (26)
- GPQA Diamond90.1%
- LiveBench Coding79.0
- LiveBench Reasoning77.6
- AIME 2024/202593.9%
- FrontierMath55.8%
- LiveBench Math81.2
- ARC-AGI-265.8%
- ARC-AGI91.0%
- FrontierMath Tier 417.1%
- DeepSWE63.4%
- FrontierCode31.8%
- APEX-Agents52.8%
- Chess Puzzles21.0%
- LiveBench 2026 Reasoning77.6
- Mystery Game Puzzles8.0%
- GDP.pdf14.0%
- LiveBench 2026 Browser84.0
- LiveBench 2026 Data Analysis76.4
- CursorBench36.8%
- FrontierSWE18.1%
- LiveBench 2026 Coding80.6
- LiveBench 2026 Long-Horizon28.4
- Surface Evolver Bench52.5%
- LiveBench 2026 Design77.2
- ProofBench21.0%
- LiveBench 2026 Research70.1
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
Mistral Large 3 675B Instruct 2512
316 GB247.1 GB file
32K 335 GB · 128K 396 GB
GLM 5.3 Flash
138 GB114.2 GB file
32K 161 GB · 128K 234 GB
Q3_K_S
Mistral Large 3 675B Instruct 2512
325 GB291.9 GB file
32K 344 GB · 128K 405 GB
GLM 5.3 Flash
not listed
Q3_K_M
Mistral Large 3 675B Instruct 2512
362 GB321.8 GB file
32K 381 GB · 128K 442 GB
GLM 5.3 Flash
158 GB149.1 GB file
32K 181 GB · 128K 254 GB
Q4_0
Mistral Large 3 675B Instruct 2512
371 GB381.7 GB file
32K 390 GB · 128K 451 GB
GLM 5.3 Flash
not listed
Q4_K_M
Mistral Large 3 675B Instruct 2512
446 GB407.0 GB file
32K 465 GB · 128K 525 GB
GLM 5.3 Flash
195 GB188.7 GB file
32K 217 GB · 128K 290 GB
Q5_K_M
Mistral Large 3 675B Instruct 2512
529 GB478.0 GB file
32K 548 GB · 128K 609 GB
GLM 5.3 Flash
231 GB244.7 GB file
32K 253 GB · 128K 326 GB
Q6_K
Mistral Large 3 675B Instruct 2512
613 GB553.3 GB file
32K 632 GB · 128K 693 GB
GLM 5.3 Flash
267 GB~265.1 GB file
32K 290 GB · 128K 362 GB
Q8_0
Mistral Large 3 675B Instruct 2512
743 GB715.7 GB file
32K 762 GB · 128K 822 GB
GLM 5.3 Flash
323 GB341.0 GB file
32K 346 GB · 128K 418 GB
15 more quants
IQ2_XXS
Mistral Large 3 675B Instruct 2512
204 GB224.8 GB file
32K 223 GB · 128K 284 GB
GLM 5.3 Flash
90.2 GB101.8 GB file
32K 113 GB · 128K 185 GB
IQ2_XS
Mistral Large 3 675B Instruct 2512
223 GB189.5 GB file
32K 242 GB · 128K 303 GB
GLM 5.3 Flash
98.2 GB92.1 GB file
32K 121 GB · 128K 193 GB
IQ2_S
Mistral Large 3 675B Instruct 2512
232 GB190.8 GB file
32K 251 GB · 128K 312 GB
GLM 5.3 Flash
102 GB113.6 GB file
32K 125 GB · 128K 197 GB
IQ2_M
Mistral Large 3 675B Instruct 2512
251 GB235.4 GB file
32K 270 GB · 128K 331 GB
GLM 5.3 Flash
not listed
IQ3_XXS
Mistral Large 3 675B Instruct 2512
288 GB279.2 GB file
32K 307 GB · 128K 368 GB
GLM 5.3 Flash
126 GB120.4 GB file
32K 149 GB · 128K 221 GB
IQ3_XS
Mistral Large 3 675B Instruct 2512
306 GB279.1 GB file
32K 325 GB · 128K 386 GB
GLM 5.3 Flash
not listed
IQ3_S
Mistral Large 3 675B Instruct 2512
not listed
GLM 5.3 Flash
138 GB149.6 GB file
32K 161 GB · 128K 234 GB
IQ3_M
Mistral Large 3 675B Instruct 2512
334 GB309.9 GB file
32K 353 GB · 128K 414 GB
GLM 5.3 Flash
146 GB150.7 GB file
32K 169 GB · 128K 242 GB
Q3_K_L
Mistral Large 3 675B Instruct 2512
381 GB321.7 GB file
32K 400 GB · 128K 460 GB
GLM 5.3 Flash
not listed
IQ4_XS
Mistral Large 3 675B Instruct 2512
399 GB360.0 GB file
32K 418 GB · 128K 479 GB
GLM 5.3 Flash
175 GB156.8 GB file
32K 197 GB · 128K 270 GB
IQ4_NL
Mistral Large 3 675B Instruct 2512
418 GB380.7 GB file
32K 437 GB · 128K 498 GB
GLM 5.3 Flash
not listed
Q4_1
Mistral Large 3 675B Instruct 2512
418 GB422.4 GB file
32K 437 GB · 128K 498 GB
GLM 5.3 Flash
not listed
Q4_K_S
Mistral Large 3 675B Instruct 2512
418 GB382.7 GB file
32K 437 GB · 128K 498 GB
GLM 5.3 Flash
not listed
Q5_K_S
Mistral Large 3 675B Instruct 2512
510 GB464.4 GB file
32K 530 GB · 128K 590 GB
GLM 5.3 Flash
not listed
BF16
Mistral Large 3 675B Instruct 2512
1485 GB1347.0 GB file
32K 1504 GB · 128K 1565 GB
GLM 5.3 Flash
644 GB641.6 GB file
32K 667 GB · 128K 740 GB
Mistral Large 3 675B Instruct 2512
Ollama · Q4_K_M
ollama run hf.co/unsloth/Mistral-Large-3-675B-Instruct-2512-GGUF:Q4_K_MGLM 5.3 Flash
Ollama · Q4_K_M
ollama run hf.co/batiai/GLM-5.3-Flash-GGUF:Q4_K_M| Spec | Mistral Large 3 675B Instruct 2512 | GLM 5.3 Flash |
|---|---|---|
| Publisher | Mistral AI | Z.ai |
| Parameters | 675B | 321.3B |
| Active parameters | 41B per token | 18B per token |
| Architecture | — | Glm5NextForConditionalGeneration |
| Context | — | 1M tokens |
| Modalities | Chat, Function-calling | Vision, Function-calling |
| License | Apache 2.0 | MIT |
| Released | Nov 2025 | Aug 2026 |
Frequently Asked Questions
Which is better, Mistral Large 3 675B Instruct 2512 or GLM 5.3 Flash?
GLM 5.3 Flash leads llmrun Score 124.1 to 89.6; neither fits 24 GB. Choose Mistral Large 3 675B Instruct 2512 for also does chat; choose GLM 5.3 Flash for higher llmrun Score and stronger at reasoning.
Which needs less VRAM, Mistral Large 3 675B Instruct 2512 or GLM 5.3 Flash?
At Q4_K_M, Mistral Large 3 675B Instruct 2512 requires 445.5 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 Mistral Large 3 675B Instruct 2512 or GLM 5.3 Flash on a 16 GB GPU?
Mistral Large 3 675B Instruct 2512 does not fit (smallest quant needs 213.1 GB); GLM 5.3 Flash does not fit (smallest quant needs 100.7 GB).