GPT OSS 20B vs Qwen2.5 32B Instruct

GPT OSS 20B leads llmrun Score 96.4 to 80.4; both fit 24 GB at Q4_K_M; GPT OSS 20B is 5.9× faster on RTX 4090 (~190 vs ~32 tok/s).

Model A · OpenAI

GPT OSS 20B

96.4llmrun Score

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

ChatFunctions

Model B · Alibaba

Qwen2.5 32B Instruct

80.4llmrun Score

32.8B · 32K context · Apache 2.0 · Sep 2024

ChatFunctions

Which should you choose?

Choose GPT OSS 20B if you want…

Higher llmrun Score
96.4 vs 80.4
Ahead on the benchmarks
3 of 3 shared boards
Fits a 12 GB GPU
IQ4_XS · 11.8 GB; Qwen2.5 32B Instruct needs 13.6 GB at its smallest quant
5.9× faster on RTX 4090
~190 vs ~32 tok/s
Lighter on memory
12.9 vs 20.5 GB at Q4_K_M
Longer context window
128K vs 32K tokens

Qwen2.5 32B Instruct: 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%.

MemoryGPT OSS 20BQwen2.5 32B Instruct

8 GB

RTX 4060 · 8 GB tier

GPT OSS 20B

IQ2_M · ~103 tok/s

7.6 GB · up to 32Kfits

Qwen2.5 32B Instruct

Doesn't fit

smallest quant needs 13.6 GB

12 GB

RTX 3060 12GB · 12 GB tier

GPT OSS 20B

IQ4_XS · ~89 tok/s

11.8 GB · up to 16Kfits

Qwen2.5 32B Instruct

Doesn't fit

smallest quant needs 13.6 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

GPT OSS 20B

Q4_K_M · ~98 tok/s

13.1 GB · up to 128Kmore headroom

Qwen2.5 32B Instruct

IQ2_M · ~25 tok/s

15.7 GB · up to 16K

24 GBreference

RTX 4090 · 24 GB tier

GPT OSS 20B

Q4_K_M · ~190 tok/s

13.1 GB · up to 128Kmore headroom

Qwen2.5 32B Instruct

Q4_K_M · ~32 tok/stight

24.3 GB · up to 8K

32 GB

RTX 5090 · 32 GB tier

GPT OSS 20B

Q4_K_M · ~282 tok/s

13.1 GB · up to 128Kfaster

Qwen2.5 32B Instruct

Q4_K_M · ~57 tok/s

24.3 GB · up to 32K

48 GB

RTX A6000 · 48 GB tier

GPT OSS 20B

Q4_K_M · ~154 tok/s

13.1 GB · up to 128Kfaster

Qwen2.5 32B Instruct

Q4_K_M · ~24 tok/s

24.3 GB · up to 32K

Mac 32 GB

Mac Mini M4 · Macs

GPT OSS 20B

Q4_K_M · ~28 tok/s

13.1 GB · up to 128Kfaster

Qwen2.5 32B Instruct

Q4_K_M · ~4 tok/s

24.3 GB · up to 16K

Mac 64 GB

Mac Studio M4 Max · Macs

GPT OSS 20B

Q4_K_M · ~86 tok/s

13.1 GB · up to 128Kfaster

Qwen2.5 32B Instruct

Q4_K_M · ~19 tok/s

24.3 GB · up to 32K

Mac 128 GB

Mac Studio M4 Max · Macs

GPT OSS 20B

Q4_K_M · ~86 tok/s

13.1 GB · up to 128Kfaster

Qwen2.5 32B Instruct

Q4_K_M · ~19 tok/s

24.3 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

GPT OSS 20B Qwen2.5 32B Instruct

Overall

GPT OSS 20B

96.493–100

Qwen2.5 32B Instruct

80.475–86

Coding

GPT OSS 20B

101.993–111

Qwen2.5 32B Instruct

no data

Science

GPT OSS 20B

93.186–101

Qwen2.5 32B Instruct

no data

Reasoning

GPT OSS 20B

91.383–100

Qwen2.5 32B Instruct

no data

GPT OSS 20B · #69 of 106 open models · #16 of 36 that fit 24 GB

Qwen2.5 32B Instruct · #88 of 106 open models · #25 of 36 that fit 24 GB

Benchmarks

3 shared boards: GPT OSS 20B leads 3, Qwen2.5 32B Instruct leads 0 · Benchmarks imported Nov 2026

BoardGPT OSS 20BQwen2.5 32B Instruct

GPQA Diamond

GPT OSS 20B

60.8%#44/100 open

IndependentEpoch AI · Aug 2025

Qwen2.5 32B Instruct

46.1%#65/100 open

IndependentEpoch AI · Sep 2024

AIME 2024/2025

GPT OSS 20B

65.3%#36/88 open

IndependentEpoch AI · Aug 2025

Qwen2.5 32B Instruct

7.4%#67/88 open

IndependentEpoch AI · Sep 2024

MMLU-Pro

GPT OSS 20B

73.6%#33/146 open

IndependentTIGER-Lab

Qwen2.5 32B Instruct

69.2%#39/146 open

IndependentTIGER-Lab

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

Only GPT OSS 20B (8)

LMArena Text1317.3
Terminal-Bench3.4%
SciCode38.9%
WeirdML40.9%
CritPt1.4%
DTBench68.0%
LMCA14.5%
ALE-Bench566.0

Only Qwen2.5 32B Instruct (1)

MATH Level 556.1%

VRAM by quantization

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

QuantGPT OSS 20BQwen2.5 32B Instruct

Q2_K

GPT OSS 20B

9.3 GB11.5 GB file

32K 9.8 GB · 128K 11.5 GB

Qwen2.5 32B Instruct

14.8 GB12.3 GB file

32K 22.8 GB · 128K —

Q3_K_S

GPT OSS 20B

9.5 GB11.5 GB file

32K 10.0 GB · 128K 11.7 GB

Qwen2.5 32B Instruct

15.2 GB14.4 GB file

32K 23.2 GB · 128K —

Q3_K_M

GPT OSS 20B

10.6 GB11.5 GB file

32K 11.1 GB · 128K 12.8 GB

Qwen2.5 32B Instruct

16.8 GB15.9 GB file

32K 24.9 GB · 128K —

Q4_0

GPT OSS 20B

10.8 GB11.5 GB file

32K 11.3 GB · 128K 13.0 GB

Qwen2.5 32B Instruct

17.2 GB18.6 GB file

32K 25.3 GB · 128K —

Q4_K_M

GPT OSS 20B

12.9 GB11.6 GB file

32K 13.4 GB · 128K 15.1 GB

Qwen2.5 32B Instruct

20.5 GB19.9 GB file

32K 28.6 GB · 128K —

Q5_K_M

GPT OSS 20B

15.3 GB11.7 GB file

32K 15.8 GB · 128K 17.5 GB

Qwen2.5 32B Instruct

24.2 GB23.3 GB file

32K 32.2 GB · 128K —

Q6_K

GPT OSS 20B

17.6 GB12.0 GB file

32K 18.1 GB · 128K 19.8 GB

Qwen2.5 32B Instruct

27.9 GB26.9 GB file

32K 35.9 GB · 128K —

Q8_0

GPT OSS 20B

21.3 GB~20.9 GB file

32K 21.8 GB · 128K 23.5 GB

Qwen2.5 32B Instruct

33.6 GB34.8 GB file

32K 41.7 GB · 128K —

19 more quants

IQ2_XXS

GPT OSS 20B

6.1 GB~5.8 GB file

32K 6.6 GB · 128K 8.3 GB

Qwen2.5 32B Instruct

9.9 GB9.0 GB file

32K 17.9 GB · 128K —

IQ2_XS

GPT OSS 20B

6.7 GB~6.3 GB file

32K 7.2 GB · 128K 8.9 GB

Qwen2.5 32B Instruct

10.7 GB10.0 GB file

32K 18.7 GB · 128K —

IQ2_S

GPT OSS 20B

6.9 GB~6.5 GB file

32K 7.4 GB · 128K 9.1 GB

Qwen2.5 32B Instruct

11.1 GB10.4 GB file

32K 19.1 GB · 128K —

IQ2_M

GPT OSS 20B

7.4 GB~7.1 GB file

32K 7.9 GB · 128K 9.6 GB

Qwen2.5 32B Instruct

11.9 GB11.3 GB file

32K 19.9 GB · 128K —

IQ3_XXS

GPT OSS 20B

8.5 GB11.6 GB file

32K 9.0 GB · 128K 10.7 GB

Qwen2.5 32B Instruct

13.5 GB12.8 GB file

32K 21.6 GB · 128K —

Q2_K_S

GPT OSS 20B

8.7 GB12.1 GB file

32K 9.2 GB · 128K 10.9 GB

Qwen2.5 32B Instruct

13.9 GB11.5 GB file

32K 22.0 GB · 128K —

IQ3_XS

GPT OSS 20B

9.0 GB11.6 GB file

32K 9.5 GB · 128K 11.2 GB

Qwen2.5 32B Instruct

14.4 GB13.7 GB file

32K 22.4 GB · 128K —

IQ3_S

GPT OSS 20B

9.3 GB12.1 GB file

32K 9.8 GB · 128K 11.5 GB

Qwen2.5 32B Instruct

14.8 GB14.4 GB file

32K 22.8 GB · 128K —

IQ3_M

GPT OSS 20B

9.8 GB11.6 GB file

32K 10.3 GB · 128K 12.0 GB

Qwen2.5 32B Instruct

15.6 GB14.8 GB file

32K 23.6 GB · 128K —

Q3_K_L

GPT OSS 20B

11.1 GB11.5 GB file

32K 11.6 GB · 128K 13.3 GB

Qwen2.5 32B Instruct

17.6 GB17.2 GB file

32K 25.7 GB · 128K —

IQ4_XS

GPT OSS 20B

11.6 GB11.6 GB file

32K 12.1 GB · 128K 13.8 GB

Qwen2.5 32B Instruct

18.5 GB17.7 GB file

32K 26.5 GB · 128K —

IQ4_NL

GPT OSS 20B

12.1 GB11.6 GB file

32K 12.6 GB · 128K 14.3 GB

Qwen2.5 32B Instruct

not listed

Q4_1

GPT OSS 20B

12.1 GB11.6 GB file

32K 12.6 GB · 128K 14.3 GB

Qwen2.5 32B Instruct

19.3 GB20.6 GB file

32K 27.3 GB · 128K —

Q4_K_S

GPT OSS 20B

12.1 GB11.6 GB file

32K 12.6 GB · 128K 14.3 GB

Qwen2.5 32B Instruct

19.3 GB18.8 GB file

32K 27.3 GB · 128K —

Q4_K_L

GPT OSS 20B

13.2 GB11.9 GB file

32K 13.7 GB · 128K 15.4 GB

Qwen2.5 32B Instruct

20.9 GB20.4 GB file

32K 29.0 GB · 128K —

Q5_0

GPT OSS 20B

not listed

Qwen2.5 32B Instruct

21.3 GB22.6 GB file

32K 29.4 GB · 128K —

Q5_K_S

GPT OSS 20B

14.8 GB11.7 GB file

32K 15.3 GB · 128K 17.0 GB

Qwen2.5 32B Instruct

23.4 GB22.6 GB file

32K 31.4 GB · 128K —

Q5_K_L

GPT OSS 20B

15.5 GB11.9 GB file

32K 16.0 GB · 128K 17.7 GB

Qwen2.5 32B Instruct

24.6 GB23.7 GB file

32K 32.6 GB · 128K —

BF16

GPT OSS 20B

42.2 GB~41.8 GB file

32K 42.7 GB · 128K 44.4 GB

Qwen2.5 32B Instruct

66.4 GB~65.5 GB file

32K 74.4 GB · 128K —

How to run each

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 →

Qwen2.5 32B Instruct

Ollama · Q4_K_M

$ollama run hf.co/bartowski/Qwen2.5-32B-Instruct-GGUF:Q4_K_M

All ways to run Qwen2.5 32B Instruct →

Specifications

Specifications of GPT OSS 20B and Qwen2.5 32B Instruct
Spec	GPT OSS 20B	Qwen2.5 32B Instruct
Publisher	OpenAI	Alibaba
Parameters	20.9B	32.8B
Active parameters	4.2B per token	—
Architecture	GptOssForCausalLM	Qwen2ForCausalLM
Context	128K tokens	32K tokens
Modalities	Chat, Function-calling	Chat, Function-calling
License	Apache 2.0	Apache 2.0
Released	Aug 2025	Sep 2024

Frequently Asked Questions

Which is better, GPT OSS 20B or Qwen2.5 32B Instruct?

GPT OSS 20B leads llmrun Score 96.4 to 80.4; both fit 24 GB at Q4_K_M; GPT OSS 20B is 5.9× faster on RTX 4090 (~190 vs ~32 tok/s). Choose GPT OSS 20B for higher llmrun Score and ahead on the benchmarks.

Which needs less VRAM, GPT OSS 20B or Qwen2.5 32B Instruct?

At Q4_K_M, GPT OSS 20B requires 12.9 GB while Qwen2.5 32B Instruct needs 20.5 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 190 tok/s for GPT OSS 20B (Q4_K_M) and 32 tok/s for Qwen2.5 32B Instruct (Q4_K_M), so GPT OSS 20B is faster. Estimates, ±20%.

Can I run GPT OSS 20B or Qwen2.5 32B Instruct on a 16 GB GPU?

GPT OSS 20B fits at Q4_K_M; Qwen2.5 32B Instruct fits at IQ2_M.

Which has a longer context window, GPT OSS 20B or Qwen2.5 32B Instruct?

GPT OSS 20B supports 131,072 tokens and Qwen2.5 32B Instruct supports 32,768 tokens.