Mistral Small 3.2 24B Instruct 2506 vs GPT OSS 20B

GPT OSS 20B leads llmrun Score 96.3 to 85.7; both fit 24 GB at Q4_K_M; GPT OSS 20B is 4.4× faster on RTX 4090 (~190 vs ~43 tok/s).

Model A · Mistral AI

Mistral Small 3.2 24B Instruct 2506

85.7llmrun Score

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

Chat

Model B · OpenAI

GPT OSS 20B

96.3llmrun Score

20.9B · 4.2B active · 128K context · Apache 2.0 · Aug 2025

ChatFunctions

Which should you choose?

Choose GPT OSS 20B if you want…

Higher llmrun Score
96.3 vs 85.7
Stronger at science
92.4 vs 82.4
Ahead on the benchmarks
5 of 5 shared boards
Fits a 12 GB GPU
IQ4_XS · 11.8 GB; Mistral Small 3.2 24B Instruct 2506 needs 10.3 GB at its smallest quant
4.4× faster on RTX 4090
~190 vs ~43 tok/s
Also does function-calling
Mistral Small 3.2 24B Instruct 2506 doesn't list it

Mistral Small 3.2 24B Instruct 2506: no clear edge over GPT OSS 20B in the data we have.

On your hardware

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

MemoryMistral Small 3.2 24B Instruct 2506GPT OSS 20B

8 GB

RTX 4060 · 8 GB tier

Mistral Small 3.2 24B Instruct 2506

Doesn't fit

smallest quant needs 10.3 GB

GPT OSS 20B

IQ2_M · ~103 tok/s

7.6 GB · up to 32Kfits

12 GB

RTX 3060 12GB · 12 GB tier

Mistral Small 3.2 24B Instruct 2506

IQ2_M · ~27 tok/s

11.8 GB · up to 16K

GPT OSS 20B

IQ4_XS · ~89 tok/s

11.8 GB · up to 16Kbetter quant

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Mistral Small 3.2 24B Instruct 2506

Q4_K_M · ~19 tok/stight

18.1 GB · up to 4K

GPT OSS 20B

Q4_K_M · ~98 tok/s

13.1 GB · up to 128Kmore headroom

24 GBreference

RTX 4090 · 24 GB tier

Mistral Small 3.2 24B Instruct 2506

Q4_K_M · ~43 tok/s

18.1 GB · up to 32K

GPT OSS 20B

Q4_K_M · ~190 tok/s

13.1 GB · up to 128Kfaster

32 GB

RTX 5090 · 32 GB tier

Mistral Small 3.2 24B Instruct 2506

Q4_K_M · ~77 tok/s

18.1 GB · up to 64K

GPT OSS 20B

Q4_K_M · ~282 tok/s

13.1 GB · up to 128Kfaster

48 GB

RTX A6000 · 48 GB tier

Mistral Small 3.2 24B Instruct 2506

Q4_K_M · ~33 tok/s

18.1 GB · up to 128K

GPT OSS 20B

Q4_K_M · ~154 tok/s

13.1 GB · up to 128Kfaster

Mac 32 GB

Mac Mini M4 · Macs

Mistral Small 3.2 24B Instruct 2506

Q4_K_M · ~6 tok/s

18.1 GB · up to 64K

GPT OSS 20B

Q4_K_M · ~28 tok/s

13.1 GB · up to 128Kfaster

Mac 64 GB

Mac Studio M4 Max · Macs

Mistral Small 3.2 24B Instruct 2506

Q4_K_M · ~25 tok/s

18.1 GB · up to 128K

GPT OSS 20B

Q4_K_M · ~86 tok/s

13.1 GB · up to 128Kfaster

Mac 128 GB

Mac Studio M4 Max · Macs

Mistral Small 3.2 24B Instruct 2506

Q4_K_M · ~25 tok/s

18.1 GB · up to 128K

GPT OSS 20B

Q4_K_M · ~86 tok/s

13.1 GB · up to 128Kfaster

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 3.2 24B Instruct 2506 GPT OSS 20B

Overall

Mistral Small 3.2 24B Instruct 2506

85.781–90

GPT OSS 20B

96.393–99

Coding

Mistral Small 3.2 24B Instruct 2506

no data

GPT OSS 20B

100.992–110

Science

Mistral Small 3.2 24B Instruct 2506

82.474–91

GPT OSS 20B

92.485–100

Reasoning

Mistral Small 3.2 24B Instruct 2506

no data

GPT OSS 20B

91.383–100

Mistral Small 3.2 24B Instruct 2506 · #73 of 100 open models · #20 of 35 that fit 24 GB

GPT OSS 20B · #63 of 100 open models · #15 of 35 that fit 24 GB

Benchmarks

5 shared boards: Mistral Small 3.2 24B Instruct 2506 leads 0, GPT OSS 20B leads 5 · Benchmarks imported Oct 2026

BoardMistral Small 3.2 24B Instruct 2506GPT OSS 20B

GPQA Diamond

Mistral Small 3.2 24B Instruct 2506

49.0%#55/98 open

IndependentEpoch AI · Jun 2025

GPT OSS 20B

60.8%#42/98 open

IndependentEpoch AI · Aug 2025

AIME 2024/2025

Mistral Small 3.2 24B Instruct 2506

30.3%#49/86 open

IndependentEpoch AI · Jun 2025

GPT OSS 20B

65.3%#34/86 open

IndependentEpoch AI · Aug 2025

SciCode

Mistral Small 3.2 24B Instruct 2506

26.4%#57/66 open

Lab-reportedEpoch AI · Jun 2025

GPT OSS 20B

34.4%#48/66 open

Lab-reportedEpoch AI · Aug 2025

CritPt

Mistral Small 3.2 24B Instruct 2506

0.0%#61/66 open

Lab-reportedEpoch AI · Jun 2025

GPT OSS 20B

1.4%#31/66 open

Lab-reportedEpoch AI · Aug 2025

DTBench

Mistral Small 3.2 24B Instruct 2506

59.9%#49/68 open

Lab-reportedEpoch AI · Jun 2025

GPT OSS 20B

68.0%#34/68 open

Lab-reportedEpoch AI · Aug 2025

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

LMArena Text

Mistral Small 3.2 24B Instruct 2506

1356.1#71/187 open

ArenaLMArena · Oct 2026

GPT OSS 20B

1317.4#97/187 open

ArenaLMArena · Oct 2026

Only GPT OSS 20B (5)

Terminal-Bench3.4%
MMLU-Pro73.6%
WeirdML40.9%
LMCA14.5%
ALE-Bench566.0

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 3.2 24B Instruct 2506GPT OSS 20B

Q2_K

Mistral Small 3.2 24B Instruct 2506

10.9 GB8.9 GB file

32K 17.2 GB · 128K 37.3 GB

GPT OSS 20B

9.3 GB11.5 GB file

32K 9.8 GB · 128K 11.5 GB

Q3_K_S

Mistral Small 3.2 24B Instruct 2506

11.2 GB10.4 GB file

32K 17.5 GB · 128K 37.6 GB

GPT OSS 20B

9.5 GB11.5 GB file

32K 10.0 GB · 128K 11.7 GB

Q3_K_M

Mistral Small 3.2 24B Instruct 2506

12.4 GB11.5 GB file

32K 18.7 GB · 128K 38.8 GB

GPT OSS 20B

10.6 GB11.5 GB file

32K 11.1 GB · 128K 12.8 GB

Q4_0

Mistral Small 3.2 24B Instruct 2506

12.7 GB13.5 GB file

32K 19.0 GB · 128K 39.2 GB

GPT OSS 20B

10.8 GB11.5 GB file

32K 11.3 GB · 128K 13.0 GB

Q4_K_M

Mistral Small 3.2 24B Instruct 2506

15.1 GB14.3 GB file

32K 21.4 GB · 128K 41.6 GB

GPT OSS 20B

12.9 GB11.6 GB file

32K 13.4 GB · 128K 15.1 GB

Q5_K_M

Mistral Small 3.2 24B Instruct 2506

17.8 GB16.8 GB file

32K 24.1 GB · 128K 44.3 GB

GPT OSS 20B

15.3 GB11.7 GB file

32K 15.8 GB · 128K 17.5 GB

Q6_K

Mistral Small 3.2 24B Instruct 2506

20.5 GB19.3 GB file

32K 26.8 GB · 128K 47.0 GB

GPT OSS 20B

17.6 GB12.0 GB file

32K 18.1 GB · 128K 19.8 GB

Q8_0

Mistral Small 3.2 24B Instruct 2506

24.7 GB25.1 GB file

32K 31.0 GB · 128K 51.2 GB

GPT OSS 20B

21.3 GB~20.9 GB file

32K 21.8 GB · 128K 23.5 GB

19 more quants

IQ2_XXS

Mistral Small 3.2 24B Instruct 2506

7.3 GB6.8 GB file

32K 13.6 GB · 128K 33.7 GB

GPT OSS 20B

6.1 GB~5.8 GB file

32K 6.6 GB · 128K 8.3 GB

IQ2_XS

Mistral Small 3.2 24B Instruct 2506

7.9 GB7.2 GB file

32K 14.2 GB · 128K 34.3 GB

GPT OSS 20B

6.7 GB~6.3 GB file

32K 7.2 GB · 128K 8.9 GB

IQ2_S

Mistral Small 3.2 24B Instruct 2506

8.2 GB7.5 GB file

32K 14.5 GB · 128K 34.6 GB

GPT OSS 20B

6.9 GB~6.5 GB file

32K 7.4 GB · 128K 9.1 GB

IQ2_M

Mistral Small 3.2 24B Instruct 2506

8.8 GB8.2 GB file

32K 15.1 GB · 128K 35.2 GB

GPT OSS 20B

7.4 GB~7.1 GB file

32K 7.9 GB · 128K 9.6 GB

IQ3_XXS

Mistral Small 3.2 24B Instruct 2506

10.0 GB9.4 GB file

32K 16.3 GB · 128K 36.4 GB

GPT OSS 20B

8.5 GB11.6 GB file

32K 9.0 GB · 128K 10.7 GB

Q2_K_S

Mistral Small 3.2 24B Instruct 2506

10.3 GB8.3 GB file

32K 16.6 GB · 128K 36.7 GB

GPT OSS 20B

8.7 GB12.1 GB file

32K 9.2 GB · 128K 10.9 GB

IQ3_XS

Mistral Small 3.2 24B Instruct 2506

10.6 GB9.9 GB file

32K 16.9 GB · 128K 37.0 GB

GPT OSS 20B

9.0 GB11.6 GB file

32K 9.5 GB · 128K 11.2 GB

IQ3_S

Mistral Small 3.2 24B Instruct 2506

10.9 GB10.4 GB file

32K 17.2 GB · 128K 37.3 GB

GPT OSS 20B

9.3 GB12.1 GB file

32K 9.8 GB · 128K 11.5 GB

IQ3_M

Mistral Small 3.2 24B Instruct 2506

11.5 GB10.7 GB file

32K 17.8 GB · 128K 37.9 GB

GPT OSS 20B

9.8 GB11.6 GB file

32K 10.3 GB · 128K 12.0 GB

Q3_K_L

Mistral Small 3.2 24B Instruct 2506

13.0 GB12.4 GB file

32K 19.3 GB · 128K 39.5 GB

GPT OSS 20B

11.1 GB11.5 GB file

32K 11.6 GB · 128K 13.3 GB

IQ4_XS

Mistral Small 3.2 24B Instruct 2506

13.6 GB12.8 GB file

32K 19.9 GB · 128K 40.1 GB

GPT OSS 20B

11.6 GB11.6 GB file

32K 12.1 GB · 128K 13.8 GB

IQ4_NL

Mistral Small 3.2 24B Instruct 2506

14.2 GB13.5 GB file

32K 20.5 GB · 128K 40.7 GB

GPT OSS 20B

12.1 GB11.6 GB file

32K 12.6 GB · 128K 14.3 GB

Q4_1

Mistral Small 3.2 24B Instruct 2506

14.2 GB14.9 GB file

32K 20.5 GB · 128K 40.7 GB

GPT OSS 20B

12.1 GB11.6 GB file

32K 12.6 GB · 128K 14.3 GB

Q4_K_S

Mistral Small 3.2 24B Instruct 2506

14.2 GB13.5 GB file

32K 20.5 GB · 128K 40.7 GB

GPT OSS 20B

12.1 GB11.6 GB file

32K 12.6 GB · 128K 14.3 GB

Q4_K_L

Mistral Small 3.2 24B Instruct 2506

15.4 GB14.8 GB file

32K 21.7 GB · 128K 41.9 GB

GPT OSS 20B

13.2 GB11.9 GB file

32K 13.7 GB · 128K 15.4 GB

Q5_0

Mistral Small 3.2 24B Instruct 2506

15.7 GB16.4 GB file

32K 22.0 GB · 128K 42.2 GB

GPT OSS 20B

not listed

Q5_K_S

Mistral Small 3.2 24B Instruct 2506

17.2 GB16.3 GB file

32K 23.5 GB · 128K 43.7 GB

GPT OSS 20B

14.8 GB11.7 GB file

32K 15.3 GB · 128K 17.0 GB

Q5_K_L

Mistral Small 3.2 24B Instruct 2506

18.1 GB17.2 GB file

32K 24.4 GB · 128K 44.6 GB

GPT OSS 20B

15.5 GB11.9 GB file

32K 16.0 GB · 128K 17.7 GB

BF16

Mistral Small 3.2 24B Instruct 2506

48.7 GB47.2 GB file

32K 55.0 GB · 128K 75.2 GB

GPT OSS 20B

42.2 GB~41.8 GB file

32K 42.7 GB · 128K 44.4 GB

How to run each

Mistral Small 3.2 24B Instruct 2506

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q4_K_M

All ways to run Mistral Small 3.2 24B Instruct 2506 →

GPT OSS 20B

Ollama · Q4_K_M

$ollama run hf.co/unsloth/gpt-oss-20b-GGUF:Q4_K_M

All ways to run GPT OSS 20B →

Specifications

Specifications of Mistral Small 3.2 24B Instruct 2506 and GPT OSS 20B
Spec	Mistral Small 3.2 24B Instruct 2506	GPT OSS 20B
Publisher	Mistral AI	OpenAI
Parameters	24.0B	20.9B
Active parameters	—	4.2B per token
Architecture	Mistral3ForConditionalGeneration	GptOssForCausalLM
Context	128K tokens	128K tokens
Modalities	Chat	Chat, Function-calling
License	Apache 2.0	Apache 2.0
Released	Jun 2025	Aug 2025

Frequently Asked Questions

Which is better, Mistral Small 3.2 24B Instruct 2506 or GPT OSS 20B?

GPT OSS 20B leads llmrun Score 96.3 to 85.7; both fit 24 GB at Q4_K_M; GPT OSS 20B is 4.4× faster on RTX 4090 (~190 vs ~43 tok/s). Choose GPT OSS 20B for higher llmrun Score and stronger at science.

Which needs less VRAM, Mistral Small 3.2 24B Instruct 2506 or GPT OSS 20B?

At Q4_K_M, Mistral Small 3.2 24B Instruct 2506 requires 15.1 GB while GPT OSS 20B needs 12.9 GB, making GPT OSS 20B 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 3.2 24B Instruct 2506 (Q4_K_M) and 190 tok/s for GPT OSS 20B (Q4_K_M), so GPT OSS 20B is faster. Estimates, ±20%.

Can I run Mistral Small 3.2 24B Instruct 2506 or GPT OSS 20B on a 16 GB GPU?

Mistral Small 3.2 24B Instruct 2506 fits at Q4_K_M; GPT OSS 20B fits at Q4_K_M.

Which has a longer context window, Mistral Small 3.2 24B Instruct 2506 or GPT OSS 20B?

Mistral Small 3.2 24B Instruct 2506 supports 131,072 tokens and GPT OSS 20B supports 131,072 tokens.