Mistral Small 3.1 24B Instruct 2503 vs Mixtral 8x7B Instruct v0.1

Model A · Mistral AI

Mistral Small 3.1 24B Instruct 2503

79.0llmrun Score

24.0B · 128K context · Apache 2.0 · Mar 2025

Chat

Model B · Mistral AI

Mixtral 8x7B Instruct v0.1

65.1llmrun Score

46.7B · 12.9B active · 32K context · Apache 2.0 · Dec 2023

Chat

Which should you choose?

Choose Mistral Small 3.1 24B Instruct 2503 if you want…

Higher llmrun Score
79.0 vs 65.1
Ahead on the benchmarks
3 of 3 shared boards
Fits a 16 GB GPU
Q4_K_M · 18.1 GB; Mixtral 8x7B Instruct v0.1 needs 15.3 GB at its smallest quant
Lighter on memory
15.1 vs 28.6 GB at Q4_K_M
Longer context window
128K vs 32K tokens
Newer release
Mar 2025 vs Dec 2023

Choose Mixtral 8x7B Instruct v0.1 if you want…

2.1× faster on RTX 4090
~92 vs ~43 tok/s

On your hardware

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

MemoryMistral Small 3.1 24B Instruct 2503Mixtral 8x7B Instruct v0.1

8 GB

RTX 4060 · 8 GB tier

Mistral Small 3.1 24B Instruct 2503

Doesn't fit

smallest quant needs 10.3 GB

Mixtral 8x7B Instruct v0.1

Doesn't fit

smallest quant needs 15.3 GB

12 GB

RTX 3060 12GB · 12 GB tier

Mistral Small 3.1 24B Instruct 2503

IQ2_M · ~27 tok/s

11.8 GB · up to 16Kfits

Mixtral 8x7B Instruct v0.1

Doesn't fit

smallest quant needs 15.3 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Mistral Small 3.1 24B Instruct 2503

Q4_K_M · ~19 tok/stight

18.1 GB · up to 4K

Mixtral 8x7B Instruct v0.1

IQ2_XXS · ~69 tok/s

15.3 GB · up to 16Kmore headroom

24 GBreference

RTX 4090 · 24 GB tier

Mistral Small 3.1 24B Instruct 2503

Q4_K_M · ~43 tok/s

18.1 GB · up to 32Kmore headroom

Mixtral 8x7B Instruct v0.1

IQ3_M · ~92 tok/s

23.5 GB · up to 16K

32 GB

RTX 5090 · 32 GB tier

Mistral Small 3.1 24B Instruct 2503

Q4_K_M · ~77 tok/s

18.1 GB · up to 64K

Mixtral 8x7B Instruct v0.1

Q4_K_M · ~117 tok/s

30.5 GB · up to 16Kfaster

48 GB

RTX A6000 · 48 GB tier

Mistral Small 3.1 24B Instruct 2503

Q4_K_M · ~33 tok/s

18.1 GB · up to 128K

Mixtral 8x7B Instruct v0.1

Q4_K_M · ~57 tok/s

30.5 GB · up to 32Kfaster

Mac 32 GB

Mac Mini M4 · Macs

Mistral Small 3.1 24B Instruct 2503

Q4_K_M · ~6 tok/s

18.1 GB · up to 64Kmore headroom

Mixtral 8x7B Instruct v0.1

IQ4_XS · ~11 tok/s

27.6 GB · up to 16K

Mac 64 GB

Mac Studio M4 Max · Macs

Mistral Small 3.1 24B Instruct 2503

Q4_K_M · ~25 tok/s

18.1 GB · up to 128K

Mixtral 8x7B Instruct v0.1

Q4_K_M · ~37 tok/s

30.5 GB · up to 32Kfaster

Mac 128 GB

Mac Studio M4 Max · Macs

Mistral Small 3.1 24B Instruct 2503

Q4_K_M · ~25 tok/s

18.1 GB · up to 128K

Mixtral 8x7B Instruct v0.1

Q4_K_M · ~37 tok/s

30.5 GB · up to 32Kfaster

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 Small 3.1 24B Instruct 2503 Mixtral 8x7B Instruct v0.1

Overall

Mistral Small 3.1 24B Instruct 2503

79.073–85

Mixtral 8x7B Instruct v0.1

65.158–72

Science

Mistral Small 3.1 24B Instruct 2503

81.373–90

Mixtral 8x7B Instruct v0.1

no data

Reasoning

Mistral Small 3.1 24B Instruct 2503

no data

Mixtral 8x7B Instruct v0.1

68.755–82

Mistral Small 3.1 24B Instruct 2503 · #86 of 100 open models · #26 of 35 that fit 24 GB

Mixtral 8x7B Instruct v0.1 · #96 of 100 open models · #31 of 35 that fit 24 GB

Benchmarks

3 shared boards: Mistral Small 3.1 24B Instruct 2503 leads 3, Mixtral 8x7B Instruct v0.1 leads 0 · Benchmarks imported Oct 2026

BoardMistral Small 3.1 24B Instruct 2503Mixtral 8x7B Instruct v0.1

GPQA Diamond

Mistral Small 3.1 24B Instruct 2503

47.5%#59/98 open

IndependentEpoch AI · Mar 2025

Mixtral 8x7B Instruct v0.1

30.6%#81/98 open

IndependentEpoch AI · Dec 2023

MATH Level 5

Mistral Small 3.1 24B Instruct 2503

46.8%#16/39 open

IndependentEpoch AI · Mar 2025

Mixtral 8x7B Instruct v0.1

10.0%#34/39 open

IndependentEpoch AI · Dec 2023

DTBench

Mistral Small 3.1 24B Instruct 2503

58.6%#52/68 open

Lab-reportedEpoch AI · Mar 2025

Mixtral 8x7B Instruct v0.1

49.6%#60/68 open

Lab-reportedEpoch AI · Dec 2023

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

LMArena Text

Mistral Small 3.1 24B Instruct 2503

1302.7#107/187 open

ArenaLMArena · Oct 2026

Mixtral 8x7B Instruct v0.1

1197.3#147/187 open

ArenaLMArena · Oct 2026

Only Mistral Small 3.1 24B Instruct 2503 (3)

Only Mixtral 8x7B Instruct v0.1 (2)

MMLU-Pro43.3%
ForecastBench56.3

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 Small 3.1 24B Instruct 2503Mixtral 8x7B Instruct v0.1

Q2_K

Mistral Small 3.1 24B Instruct 2503

10.9 GB8.9 GB file

32K 17.2 GB · 128K 37.3 GB

Mixtral 8x7B Instruct v0.1

20.4 GB15.6 GB file

32K 24.5 GB · 128K —

Q3_K_S

Mistral Small 3.1 24B Instruct 2503

11.2 GB10.4 GB file

32K 17.5 GB · 128K 37.6 GB

Mixtral 8x7B Instruct v0.1

21.0 GB20.4 GB file

32K 25.0 GB · 128K —

Q3_K_M

Mistral Small 3.1 24B Instruct 2503

12.4 GB11.5 GB file

32K 18.7 GB · 128K 38.8 GB

Mixtral 8x7B Instruct v0.1

23.3 GB20.4 GB file

32K 27.4 GB · 128K —

Q4_0

Mistral Small 3.1 24B Instruct 2503

12.7 GB13.5 GB file

32K 19.0 GB · 128K 39.2 GB

Mixtral 8x7B Instruct v0.1

23.9 GB26.4 GB file

32K 28.0 GB · 128K —

Q4_K_M

Mistral Small 3.1 24B Instruct 2503

15.1 GB14.3 GB file

32K 21.4 GB · 128K 41.6 GB

Mixtral 8x7B Instruct v0.1

28.6 GB26.4 GB file

32K 32.6 GB · 128K —

Q5_K_M

Mistral Small 3.1 24B Instruct 2503

17.8 GB16.8 GB file

32K 24.1 GB · 128K 44.3 GB

Mixtral 8x7B Instruct v0.1

33.8 GB32.2 GB file

32K 37.9 GB · 128K —

Q6_K

Mistral Small 3.1 24B Instruct 2503

20.5 GB19.3 GB file

32K 26.8 GB · 128K 47.0 GB

Mixtral 8x7B Instruct v0.1

39.1 GB38.4 GB file

32K 43.1 GB · 128K —

Q8_0

Mistral Small 3.1 24B Instruct 2503

24.7 GB25.1 GB file

32K 31.0 GB · 128K 51.2 GB

Mixtral 8x7B Instruct v0.1

47.3 GB49.6 GB file

32K 51.3 GB · 128K —

20 more quants

IQ2_XXS

Mistral Small 3.1 24B Instruct 2503

7.3 GB6.8 GB file

32K 13.6 GB · 128K 33.7 GB

Mixtral 8x7B Instruct v0.1

13.4 GB12.6 GB file

32K 17.4 GB · 128K —

IQ2_XS

Mistral Small 3.1 24B Instruct 2503

7.9 GB7.2 GB file

32K 14.2 GB · 128K 34.3 GB

Mixtral 8x7B Instruct v0.1

14.6 GB13.9 GB file

32K 18.6 GB · 128K —

IQ2_S

Mistral Small 3.1 24B Instruct 2503

8.2 GB7.5 GB file

32K 14.5 GB · 128K 34.6 GB

Mixtral 8x7B Instruct v0.1

15.2 GB14.1 GB file

32K 19.2 GB · 128K —

IQ2_M

Mistral Small 3.1 24B Instruct 2503

8.8 GB8.2 GB file

32K 15.1 GB · 128K 35.2 GB

Mixtral 8x7B Instruct v0.1

16.3 GB15.5 GB file

32K 20.4 GB · 128K —

IQ3_XXS

Mistral Small 3.1 24B Instruct 2503

10.0 GB9.4 GB file

32K 16.3 GB · 128K 36.4 GB

Mixtral 8x7B Instruct v0.1

18.7 GB18.2 GB file

32K 22.7 GB · 128K —

Q2_K_S

Mistral Small 3.1 24B Instruct 2503

10.3 GB8.3 GB file

32K 16.6 GB · 128K 36.7 GB

Mixtral 8x7B Instruct v0.1

19.3 GB16.0 GB file

32K 23.3 GB · 128K —

IQ3_XS

Mistral Small 3.1 24B Instruct 2503

10.6 GB9.9 GB file

32K 16.9 GB · 128K 37.0 GB

Mixtral 8x7B Instruct v0.1

19.8 GB19.4 GB file

32K 23.9 GB · 128K —

IQ3_S

Mistral Small 3.1 24B Instruct 2503

10.9 GB10.4 GB file

32K 17.2 GB · 128K 37.3 GB

Mixtral 8x7B Instruct v0.1

20.4 GB20.4 GB file

32K 24.5 GB · 128K —

IQ3_M

Mistral Small 3.1 24B Instruct 2503

11.5 GB10.7 GB file

32K 17.8 GB · 128K 37.9 GB

Mixtral 8x7B Instruct v0.1

21.6 GB21.4 GB file

32K 25.6 GB · 128K —

Q3_K_L

Mistral Small 3.1 24B Instruct 2503

13.0 GB12.4 GB file

32K 19.3 GB · 128K 39.5 GB

Mixtral 8x7B Instruct v0.1

24.5 GB24.2 GB file

32K 28.5 GB · 128K —

IQ4_XS

Mistral Small 3.1 24B Instruct 2503

13.6 GB12.8 GB file

32K 19.9 GB · 128K 40.1 GB

Mixtral 8x7B Instruct v0.1

25.7 GB25.1 GB file

32K 29.7 GB · 128K —

IQ4_NL

Mistral Small 3.1 24B Instruct 2503

14.2 GB13.5 GB file

32K 20.5 GB · 128K 40.7 GB

Mixtral 8x7B Instruct v0.1

not listed

Q4_1

Mistral Small 3.1 24B Instruct 2503

14.2 GB14.9 GB file

32K 20.5 GB · 128K 40.7 GB

Mixtral 8x7B Instruct v0.1

26.8 GB29.3 GB file

32K 30.9 GB · 128K —

Q4_K_S

Mistral Small 3.1 24B Instruct 2503

14.2 GB13.5 GB file

32K 20.5 GB · 128K 40.7 GB

Mixtral 8x7B Instruct v0.1

26.8 GB26.7 GB file

32K 30.9 GB · 128K —

Q4_K_L

Mistral Small 3.1 24B Instruct 2503

15.4 GB14.8 GB file

32K 21.7 GB · 128K 41.9 GB

Mixtral 8x7B Instruct v0.1

not listed

Q5_0

Mistral Small 3.1 24B Instruct 2503

15.7 GB16.3 GB file

32K 22.0 GB · 128K 42.2 GB

Mixtral 8x7B Instruct v0.1

29.8 GB32.2 GB file

32K 33.8 GB · 128K —

Q5_1

Mistral Small 3.1 24B Instruct 2503

not listed

Mixtral 8x7B Instruct v0.1

32.7 GB35.1 GB file

32K 36.7 GB · 128K —

Q5_K_S

Mistral Small 3.1 24B Instruct 2503

17.2 GB16.3 GB file

32K 23.5 GB · 128K 43.7 GB

Mixtral 8x7B Instruct v0.1

32.7 GB32.2 GB file

32K 36.7 GB · 128K —

Q5_K_L

Mistral Small 3.1 24B Instruct 2503

18.1 GB17.2 GB file

32K 24.4 GB · 128K 44.6 GB

Mixtral 8x7B Instruct v0.1

not listed

BF16

Mistral Small 3.1 24B Instruct 2503

48.7 GB47.2 GB file

32K 55.0 GB · 128K 75.2 GB

Mixtral 8x7B Instruct v0.1

94.0 GB~93.4 GB file

32K 98.0 GB · 128K —

How to run each

Mistral Small 3.1 24B Instruct 2503

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF:Q4_K_M

All ways to run Mistral Small 3.1 24B Instruct 2503 →

Mixtral 8x7B Instruct v0.1

Ollama · Q4_K_M

$ollama run hf.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF:Q4_K_M

All ways to run Mixtral 8x7B Instruct v0.1 →

Specifications

Specifications of Mistral Small 3.1 24B Instruct 2503 and Mixtral 8x7B Instruct v0.1
Spec	Mistral Small 3.1 24B Instruct 2503	Mixtral 8x7B Instruct v0.1
Publisher	Mistral AI	Mistral AI
Parameters	24.0B	46.7B
Active parameters	—	13B per token
Architecture	Mistral3ForConditionalGeneration	MixtralForCausalLM
Context	128K tokens	32K tokens
Modalities	Chat	Chat
License	Apache 2.0	Apache 2.0
Released	Mar 2025	Dec 2023

Frequently Asked Questions

Which is better, Mistral Small 3.1 24B Instruct 2503 or Mixtral 8x7B Instruct v0.1?

Mistral Small 3.1 24B Instruct 2503 leads llmrun Score 79.0 to 65.1; both fit 24 GB (Mistral Small 3.1 24B Instruct 2503 at Q4_K_M, Mixtral 8x7B Instruct v0.1 at IQ3_M); Mixtral 8x7B Instruct v0.1 is 2.1× faster on RTX 4090 (~92 vs ~43 tok/s). Choose Mistral Small 3.1 24B Instruct 2503 for higher llmrun Score and ahead on the benchmarks; choose Mixtral 8x7B Instruct v0.1 for 2.1× faster on RTX 4090.

Which needs less VRAM, Mistral Small 3.1 24B Instruct 2503 or Mixtral 8x7B Instruct v0.1?

At Q4_K_M, Mistral Small 3.1 24B Instruct 2503 requires 15.1 GB while Mixtral 8x7B Instruct v0.1 needs 28.6 GB, making Mistral Small 3.1 24B Instruct 2503 the easier model to run on your local setup.

Which is faster on RTX 4090?

Estimated decode speed on RTX 4090 is about 43 tok/s for Mistral Small 3.1 24B Instruct 2503 (Q4_K_M) and 92 tok/s for Mixtral 8x7B Instruct v0.1 (IQ3_M), so Mixtral 8x7B Instruct v0.1 is faster. Estimates, ±20%.

Can I run Mistral Small 3.1 24B Instruct 2503 or Mixtral 8x7B Instruct v0.1 on a 16 GB GPU?

Mistral Small 3.1 24B Instruct 2503 fits at Q4_K_M; Mixtral 8x7B Instruct v0.1 fits at IQ2_XXS.

Which has a longer context window, Mistral Small 3.1 24B Instruct 2503 or Mixtral 8x7B Instruct v0.1?

Mistral Small 3.1 24B Instruct 2503 supports 131,072 tokens and Mixtral 8x7B Instruct v0.1 supports 32,768 tokens.