Mistral Large Instruct 2411 vs Qwen3 235B A22B Thinking 2507

Qwen3 235B A22B Thinking 2507 leads llmrun Score 108.4 to 82.5; neither fits 24 GB.

Run Qwen3 235B A22B Thinking 2507 in the cloud →

Model A · Mistral AI

Mistral Large Instruct 2411

82.5llmrun Score

122.6B · 128K context · Other · Nov 2024

Chat

Model B · Alibaba

Qwen3 235B A22B Thinking 2507

108.4llmrun Score

235.1B · 22.2B active · 256K context · Apache 2.0 · Jul 2025

ChatFunctions

Which should you choose?

Choose Mistral Large Instruct 2411 if you want…

Fits a Mac 64 GB
Q3_K_S · 59.9 GB; Qwen3 235B A22B Thinking 2507 needs 72.4 GB at its smallest quant
Lighter on memory
74.6 vs 141.6 GB at Q4_K_M

Choose Qwen3 235B A22B Thinking 2507 if you want…

Higher llmrun Score
108.4 vs 82.5
Stronger at reasoning
107.6 vs 86.9
Ahead on the benchmarks
5 of 5 shared boards
Longer context window
256K vs 128K tokens
Also does function-calling
Mistral Large Instruct 2411 doesn't list it
More permissive license
Apache 2.0 vs Other

On your hardware

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

MemoryMistral Large Instruct 2411Qwen3 235B A22B Thinking 2507

8 GB

RTX 4060 · 8 GB tier

Mistral Large Instruct 2411

Doesn't fit

smallest quant needs 58.3 GB

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

12 GB

RTX 3060 12GB · 12 GB tier

Mistral Large Instruct 2411

Doesn't fit

smallest quant needs 58.3 GB

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Mistral Large Instruct 2411

Doesn't fit

smallest quant needs 58.3 GB

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

24 GBreference

RTX 4090 · 24 GB tier

Mistral Large Instruct 2411

Doesn't fit

smallest quant needs 58.3 GB

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

32 GB

RTX 5090 · 32 GB tier

Mistral Large Instruct 2411

Doesn't fit

smallest quant needs 58.3 GB

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

48 GB

RTX A6000 · 48 GB tier

Mistral Large Instruct 2411

Doesn't fit

smallest quant needs 58.3 GB

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

Mac 32 GB

Mac Mini M4 · Macs

Mistral Large Instruct 2411

Doesn't fit

smallest quant needs 58.3 GB

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

Mac 64 GB

Mac Studio M4 Max · Macs

Mistral Large Instruct 2411

Q3_K_S · ~7 tok/s

59.9 GB · up to 16Kfits

Qwen3 235B A22B Thinking 2507

Doesn't fit

smallest quant needs 72.4 GB

Mac 128 GB

Mac Studio M4 Max · Macs

Mistral Large Instruct 2411

Q4_K_M · ~5 tok/s

79.8 GB · up to 128Kmore headroom

Qwen3 235B A22B Thinking 2507

Q3_K_L · ~21 tok/s

122.4 GB · up to 32K

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

Mistral Large Instruct 2411 Qwen3 235B A22B Thinking 2507

Overall

Mistral Large Instruct 2411

82.578–87

Qwen3 235B A22B Thinking 2507

108.4105–112

Coding

Mistral Large Instruct 2411

no data

Qwen3 235B A22B Thinking 2507

102.392–113

Science

Mistral Large Instruct 2411

no data

Qwen3 235B A22B Thinking 2507

107.599–116

Reasoning

Mistral Large Instruct 2411

86.977–96

Qwen3 235B A22B Thinking 2507

107.6100–116

Mistral Large Instruct 2411 · #83 of 106 open models · #40 of 62 that fit ≤96 GB

Qwen3 235B A22B Thinking 2507 · #37 of 106 open models · #17 of 82 that fit ≤192 GB

Benchmarks

5 shared boards: Mistral Large Instruct 2411 leads 0, Qwen3 235B A22B Thinking 2507 leads 5 · Benchmarks imported Nov 2026

BoardMistral Large Instruct 2411Qwen3 235B A22B Thinking 2507

GPQA Diamond

Mistral Large Instruct 2411

51.3%#54/100 open

IndependentEpoch AI · Nov 2024

Qwen3 235B A22B Thinking 2507

80.0%#27/100 open

IndependentEpoch AI · Jul 2025

AIME 2024/2025

Mistral Large Instruct 2411

7.8%#65/88 open

IndependentEpoch AI · Nov 2024

Qwen3 235B A22B Thinking 2507

86.7%#21/88 open

IndependentEpoch AI · Jul 2025

MMLU-Pro

Mistral Large Instruct 2411

67.9%#42/146 open

IndependentTIGER-Lab

Qwen3 235B A22B Thinking 2507

84.5%#11/146 open

IndependentTIGER-Lab

DTBench

Mistral Large Instruct 2411

60.8%#48/70 open

Lab-reportedEpoch AI · Nov 2024

Qwen3 235B A22B Thinking 2507

80.3%#23/70 open

Lab-reportedEpoch AI · Jul 2025

ForecastBench

Mistral Large Instruct 2411

61.5#13/24 open

Lab-reportedEpoch AI · Nov 2024

Qwen3 235B A22B Thinking 2507

62.2#9/24 open

Lab-reportedEpoch AI · Jul 2025

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

LMArena Text

Mistral Large Instruct 2411

1305.6#104/188 open

ArenaLMArena · Oct 2026

Qwen3 235B A22B Thinking 2507

1400.1#50/188 open

ArenaLMArena · Oct 2026

Only Mistral Large Instruct 2411 (1)

MATH Level 550.3%

Only Qwen3 235B A22B Thinking 2507 (8)

VRAM by quantization

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

QuantMistral Large Instruct 2411Qwen3 235B A22B Thinking 2507

Q2_K

Mistral Large Instruct 2411

53.2 GB45.2 GB file

32K 64.2 GB · 128K 99.7 GB

Qwen3 235B A22B Thinking 2507

100 GB85.7 GB file

32K 103 GB · 128K 113 GB

Q3_K_S

Mistral Large Instruct 2411

54.7 GB52.8 GB file

32K 65.8 GB · 128K 101 GB

Qwen3 235B A22B Thinking 2507

103 GB101.4 GB file

32K 106 GB · 128K 116 GB

Q3_K_M

Mistral Large Instruct 2411

60.8 GB59.1 GB file

32K 71.9 GB · 128K 107 GB

Qwen3 235B A22B Thinking 2507

115 GB112.4 GB file

32K 118 GB · 128K 128 GB

Q4_0

Mistral Large Instruct 2411

not listed

Qwen3 235B A22B Thinking 2507

118 GB133.1 GB file

32K 121 GB · 128K 130 GB

Q4_K_M

Mistral Large Instruct 2411

74.6 GB73.2 GB file

32K 85.7 GB · 128K 121 GB

Qwen3 235B A22B Thinking 2507

142 GB142.2 GB file

32K 145 GB · 128K 154 GB

Q5_K_M

Mistral Large Instruct 2411

88.4 GB86.5 GB file

32K 99.5 GB · 128K 135 GB

Qwen3 235B A22B Thinking 2507

168 GB166.8 GB file

32K 171 GB · 128K 180 GB

Q6_K

Mistral Large Instruct 2411

102 GB~101.2 GB file

32K 113 GB · 128K 149 GB

Qwen3 235B A22B Thinking 2507

194 GB193.0 GB file

32K 197 GB · 128K 207 GB

Q8_0

Mistral Large Instruct 2411

124 GB~122.6 GB file

32K 135 GB · 128K 170 GB

Qwen3 235B A22B Thinking 2507

236 GB249.9 GB file

32K 239 GB · 128K 248 GB

13 more quants

IQ2_XS

Mistral Large Instruct 2411

not listed

Qwen3 235B A22B Thinking 2507

71.0 GB65.6 GB file

32K 74.0 GB · 128K 83.5 GB

IQ2_S

Mistral Large Instruct 2411

not listed

Qwen3 235B A22B Thinking 2507

74.0 GB66.1 GB file

32K 76.9 GB · 128K 86.4 GB

IQ2_M

Mistral Large Instruct 2411

not listed

Qwen3 235B A22B Thinking 2507

79.8 GB78.6 GB file

32K 82.8 GB · 128K 92.3 GB

IQ3_XXS

Mistral Large Instruct 2411

not listed

Qwen3 235B A22B Thinking 2507

91.6 GB93.1 GB file

32K 94.6 GB · 128K 104 GB

IQ3_XS

Mistral Large Instruct 2411

not listed

Qwen3 235B A22B Thinking 2507

97.5 GB96.9 GB file

32K 100 GB · 128K 110 GB

IQ3_M

Mistral Large Instruct 2411

not listed

Qwen3 235B A22B Thinking 2507

106 GB107.3 GB file

32K 109 GB · 128K 119 GB

Q3_K_L

Mistral Large Instruct 2411

63.9 GB64.6 GB file

32K 75.0 GB · 128K 110 GB

Qwen3 235B A22B Thinking 2507

121 GB111.2 GB file

32K 124 GB · 128K 133 GB

IQ4_XS

Mistral Large Instruct 2411

not listed

Qwen3 235B A22B Thinking 2507

127 GB125.5 GB file

32K 130 GB · 128K 139 GB

IQ4_NL

Mistral Large Instruct 2411

not listed

Qwen3 235B A22B Thinking 2507

133 GB133.1 GB file

32K 136 GB · 128K 145 GB

Q4_1

Mistral Large Instruct 2411

not listed

Qwen3 235B A22B Thinking 2507

133 GB147.2 GB file

32K 136 GB · 128K 145 GB

Q4_K_S

Mistral Large Instruct 2411

70.0 GB69.6 GB file

32K 81.1 GB · 128K 117 GB

Qwen3 235B A22B Thinking 2507

133 GB133.7 GB file

32K 136 GB · 128K 145 GB

Q5_K_S

Mistral Large Instruct 2411

85.3 GB84.4 GB file

32K 96.4 GB · 128K 132 GB

Qwen3 235B A22B Thinking 2507

162 GB161.9 GB file

32K 165 GB · 128K 175 GB

BF16

Mistral Large Instruct 2411

246 GB~245.2 GB file

32K 257 GB · 128K 293 GB

Qwen3 235B A22B Thinking 2507

471 GB470.3 GB file

32K 474 GB · 128K 483 GB

How to run each

Mistral Large Instruct 2411

Ollama · Q4_K_M

$ollama run hf.co/MaziyarPanahi/Mistral-Large-Instruct-2411-GGUF:Q4_K_M

All ways to run Mistral Large Instruct 2411 →

Qwen3 235B A22B Thinking 2507

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF:Q4_K_M

All ways to run Qwen3 235B A22B Thinking 2507 →

Specifications

Specifications of Mistral Large Instruct 2411 and Qwen3 235B A22B Thinking 2507
Spec	Mistral Large Instruct 2411	Qwen3 235B A22B Thinking 2507
Publisher	Mistral AI	Alibaba
Parameters	122.6B	235.1B
Active parameters	—	22B per token
Architecture	MistralForCausalLM	Qwen3MoeForCausalLM
Context	128K tokens	256K tokens
Modalities	Chat	Chat, Function-calling
License	Other	Apache 2.0
Released	Nov 2024	Jul 2025

Frequently Asked Questions

Which is better, Mistral Large Instruct 2411 or Qwen3 235B A22B Thinking 2507?

Qwen3 235B A22B Thinking 2507 leads llmrun Score 108.4 to 82.5; neither fits 24 GB. Choose Mistral Large Instruct 2411 for fits a Mac 64 GB and lighter on memory; choose Qwen3 235B A22B Thinking 2507 for higher llmrun Score and stronger at reasoning.

Which needs less VRAM, Mistral Large Instruct 2411 or Qwen3 235B A22B Thinking 2507?

At Q4_K_M, Mistral Large Instruct 2411 requires 74.6 GB while Qwen3 235B A22B Thinking 2507 needs 141.6 GB, making Mistral Large Instruct 2411 the easier model to run on your local setup.

Can I run Mistral Large Instruct 2411 or Qwen3 235B A22B Thinking 2507 on a 16 GB GPU?

Mistral Large Instruct 2411 does not fit (smallest quant needs 58.3 GB); Qwen3 235B A22B Thinking 2507 does not fit (smallest quant needs 72.4 GB).

Which has a longer context window, Mistral Large Instruct 2411 or Qwen3 235B A22B Thinking 2507?

Mistral Large Instruct 2411 supports 131,072 tokens and Qwen3 235B A22B Thinking 2507 supports 262,144 tokens.