GPT OSS 20B vs Qwen3.5 9B

Qwen3.5 9B leads llmrun Score 99.4 to 96.2 (ranges overlap); both fit 24 GB at Q4_K_M; GPT OSS 20B is 1.8× faster on RTX 4090 (~190 vs ~103 tok/s).

Model A · OpenAI

GPT OSS 20B

96.2llmrun Score

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

ChatFunctions

Model B · Alibaba

Qwen3.5 9B

99.4llmrun Score

9.7B · 256K context · Apache 2.0 · Feb 2026

VisionFunctions

Which should you choose?

Choose GPT OSS 20B if you want…

1.8× faster on RTX 4090
~190 vs ~103 tok/s
Also does chat
Qwen3.5 9B doesn't list it

Choose Qwen3.5 9B if you want…

Higher llmrun Score
99.4 vs 96.2, ranges overlap
Stronger at science
104.2 vs 92.4
Stronger at reasoning
97.1 vs 90.8
Ahead on the benchmarks
6 of 9 shared boards
Fits an 8 GB GPU
Q4_K_M · 6.6 GB; GPT OSS 20B needs 6.3 GB at its smallest quant
Lighter on memory
6.4 vs 12.9 GB at Q4_K_M

On your hardware

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

MemoryGPT OSS 20BQwen3.5 9B

8 GB

RTX 4060 · 8 GB tier

GPT OSS 20B

IQ2_M · ~103 tok/s

7.6 GB · up to 32K

Qwen3.5 9B

Q4_K_M · ~28 tok/s

6.6 GB · up to 32Kmore headroom

12 GB

RTX 3060 12GB · 12 GB tier

GPT OSS 20B

IQ4_XS · ~89 tok/s

11.8 GB · up to 16K

Qwen3.5 9B

Q4_K_M · ~37 tok/s

6.6 GB · up to 128Kmore headroom

16 GB

RTX 5060 Ti 16GB · 16 GB tier

GPT OSS 20B

Q4_K_M · ~98 tok/s

13.1 GB · up to 128Kfaster

Qwen3.5 9B

Q4_K_M · ~46 tok/s

6.6 GB · up to 256K

24 GBreference

RTX 4090 · 24 GB tier

GPT OSS 20B

Q4_K_M · ~190 tok/s

13.1 GB · up to 128Kfaster

Qwen3.5 9B

Q4_K_M · ~103 tok/s

6.6 GB · up to 256K

32 GB

RTX 5090 · 32 GB tier

GPT OSS 20B

Q4_K_M · ~282 tok/s

13.1 GB · up to 128Kfaster

Qwen3.5 9B

Q4_K_M · ~183 tok/s

6.6 GB · up to 256K

48 GB

RTX A6000 · 48 GB tier

GPT OSS 20B

Q4_K_M · ~154 tok/s

13.1 GB · up to 128Kfaster

Qwen3.5 9B

Q4_K_M · ~79 tok/s

6.6 GB · up to 256K

Mac 32 GB

Mac Mini M4 · Macs

GPT OSS 20B

Q4_K_M · ~28 tok/s

13.1 GB · up to 128Kfaster

Qwen3.5 9B

Q4_K_M · ~13 tok/s

6.6 GB · up to 256K

Mac 64 GB

Mac Studio M4 Max · Macs

GPT OSS 20B

Q4_K_M · ~86 tok/s

13.1 GB · up to 128Kfaster

Qwen3.5 9B

Q4_K_M · ~60 tok/s

6.6 GB · up to 256K

Mac 128 GB

Mac Studio M4 Max · Macs

GPT OSS 20B

Q4_K_M · ~86 tok/s

13.1 GB · up to 128Kfaster

Qwen3.5 9B

Q4_K_M · ~60 tok/s

6.6 GB · up to 256K

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 Qwen3.5 9B

Overall

GPT OSS 20B

96.293–99

Qwen3.5 9B

99.496–103

Coding

GPT OSS 20B

100.992–110

Qwen3.5 9B

no data

Science

GPT OSS 20B

92.485–100

Qwen3.5 9B

104.296–112

Reasoning

GPT OSS 20B

90.882–99

Qwen3.5 9B

97.189–105

GPT OSS 20B · #58 of 92 open models · #15 of 34 that fit 24 GB

Qwen3.5 9B · #49 of 92 open models · #10 of 34 that fit 24 GB

Benchmarks

9 shared boards: GPT OSS 20B leads 3, Qwen3.5 9B leads 6 · Benchmarks imported Oct 2026

BoardGPT OSS 20BQwen3.5 9B

GPQA Diamond

GPT OSS 20B

60.8%#41/97 open

IndependentEpoch AI · Aug 2025

Qwen3.5 9B

79.0%#25/97 open

IndependentEpoch AI · Feb 2026

AIME 2024/2025

GPT OSS 20B

65.3%#33/85 open

IndependentEpoch AI · Aug 2025

Qwen3.5 9B

61.7%#36/85 open

IndependentEpoch AI · Feb 2026

Terminal-Bench

GPT OSS 20B

3.4%#16/16 open

Lab-reportedEpoch AI · Aug 2025

Qwen3.5 9B

9.2%#15/16 open

Lab-reportedEpoch AI · Feb 2026

MMLU-Pro

GPT OSS 20B

73.6%#33/144 open

IndependentTIGER-Lab

Qwen3.5 9B

82.5%#17/144 open

IndependentTIGER-Lab

SciCode

GPT OSS 20B

34.4%#47/65 open

Lab-reportedEpoch AI · Aug 2025

Qwen3.5 9B

27.6%#54/65 open

Lab-reportedEpoch AI · Feb 2026

Chess Puzzles

GPT OSS 20B

4.0%#33/67 open

IndependentEpoch AI · Aug 2025

Qwen3.5 9B

12.0%#23/67 open

IndependentEpoch AI · Feb 2026

CritPt

GPT OSS 20B

1.4%#30/65 open

Lab-reportedEpoch AI · Aug 2025

Qwen3.5 9B

0.3%#43/65 open

Lab-reportedEpoch AI · Feb 2026

DTBench

GPT OSS 20B

68.0%#34/68 open

Lab-reportedEpoch AI · Aug 2025

Qwen3.5 9B

71.2%#31/68 open

Lab-reportedEpoch AI · Feb 2026

LMCA

GPT OSS 20B

14.5%#43/54 open

Lab-reportedEpoch AI · Aug 2025

Qwen3.5 9B

24.5%#28/54 open

Lab-reportedEpoch AI · Feb 2026

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

Only GPT OSS 20B (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.

QuantGPT OSS 20BQwen3.5 9B

Q2_K

GPT OSS 20B

9.3 GB11.5 GB file

32K 9.8 GB · 128K 11.5 GB

Qwen3.5 9B

4.7 GB4.3 GB file

32K 5.5 GB · 128K 8.7 GB

Q3_K_S

GPT OSS 20B

9.5 GB11.5 GB file

32K 10.0 GB · 128K 11.7 GB

Qwen3.5 9B

4.8 GB4.3 GB file

32K 5.6 GB · 128K 8.8 GB

Q3_K_M

GPT OSS 20B

10.6 GB11.5 GB file

32K 11.1 GB · 128K 12.8 GB

Qwen3.5 9B

5.3 GB4.7 GB file

32K 6.1 GB · 128K 9.3 GB

Q4_0

GPT OSS 20B

10.8 GB11.5 GB file

32K 11.3 GB · 128K 13.0 GB

Qwen3.5 9B

5.4 GB5.4 GB file

32K 6.2 GB · 128K 9.4 GB

Q4_K_M

GPT OSS 20B

12.9 GB11.6 GB file

32K 13.4 GB · 128K 15.1 GB

Qwen3.5 9B

6.4 GB5.7 GB file

32K 7.2 GB · 128K 10.4 GB

Q5_K_M

GPT OSS 20B

15.3 GB11.7 GB file

32K 15.8 GB · 128K 17.5 GB

Qwen3.5 9B

7.5 GB6.6 GB file

32K 8.3 GB · 128K 11.5 GB

Q6_K

GPT OSS 20B

17.6 GB12.0 GB file

32K 18.1 GB · 128K 19.8 GB

Qwen3.5 9B

8.5 GB7.5 GB file

32K 9.3 GB · 128K 12.6 GB

Q8_0

GPT OSS 20B

21.3 GB~20.9 GB file

32K 21.8 GB · 128K 23.5 GB

Qwen3.5 9B

10.2 GB9.5 GB file

32K 11.0 GB · 128K 14.3 GB

18 more quants

IQ2_XXS

GPT OSS 20B

6.1 GB~5.8 GB file

32K 6.6 GB · 128K 8.3 GB

Qwen3.5 9B

3.2 GB3.2 GB file

32K 4.0 GB · 128K 7.3 GB

IQ2_XS

GPT OSS 20B

6.7 GB~6.3 GB file

32K 7.2 GB · 128K 8.9 GB

Qwen3.5 9B

not listed

IQ2_S

GPT OSS 20B

6.9 GB~6.5 GB file

32K 7.4 GB · 128K 9.1 GB

Qwen3.5 9B

3.6 GB3.5 GB file

32K 4.4 GB · 128K 7.6 GB

IQ2_M

GPT OSS 20B

7.4 GB~7.1 GB file

32K 7.9 GB · 128K 9.6 GB

Qwen3.5 9B

3.8 GB3.6 GB file

32K 4.6 GB · 128K 7.9 GB

IQ3_XXS

GPT OSS 20B

8.5 GB11.6 GB file

32K 9.0 GB · 128K 10.7 GB

Qwen3.5 9B

4.3 GB4.0 GB file

32K 5.1 GB · 128K 8.3 GB

Q2_K_S

GPT OSS 20B

8.7 GB12.1 GB file

32K 9.2 GB · 128K 10.9 GB

Qwen3.5 9B

not listed

IQ3_XS

GPT OSS 20B

9.0 GB11.6 GB file

32K 9.5 GB · 128K 11.2 GB

Qwen3.5 9B

4.6 GB4.8 GB file

32K 5.4 GB · 128K 8.6 GB

IQ3_S

GPT OSS 20B

9.3 GB12.1 GB file

32K 9.8 GB · 128K 11.5 GB

Qwen3.5 9B

4.7 GB3.2 GB file

32K 5.5 GB · 128K 8.7 GB

IQ3_M

GPT OSS 20B

9.8 GB11.6 GB file

32K 10.3 GB · 128K 12.0 GB

Qwen3.5 9B

4.9 GB5.0 GB file

32K 5.7 GB · 128K 8.9 GB

Q3_K_L

GPT OSS 20B

11.1 GB11.5 GB file

32K 11.6 GB · 128K 13.3 GB

Qwen3.5 9B

5.5 GB5.4 GB file

32K 6.3 GB · 128K 9.6 GB

IQ4_XS

GPT OSS 20B

11.6 GB11.6 GB file

32K 12.1 GB · 128K 13.8 GB

Qwen3.5 9B

5.8 GB5.2 GB file

32K 6.6 GB · 128K 9.8 GB

IQ4_NL

GPT OSS 20B

12.1 GB11.6 GB file

32K 12.6 GB · 128K 14.3 GB

Qwen3.5 9B

6.0 GB5.4 GB file

32K 6.8 GB · 128K 10.0 GB

Q4_1

GPT OSS 20B

12.1 GB11.6 GB file

32K 12.6 GB · 128K 14.3 GB

Qwen3.5 9B

6.0 GB5.8 GB file

32K 6.8 GB · 128K 10.0 GB

Q4_K_S

GPT OSS 20B

12.1 GB11.6 GB file

32K 12.6 GB · 128K 14.3 GB

Qwen3.5 9B

6.0 GB5.4 GB file

32K 6.8 GB · 128K 10.0 GB

Q4_K_L

GPT OSS 20B

13.2 GB11.9 GB file

32K 13.7 GB · 128K 15.4 GB

Qwen3.5 9B

6.5 GB6.9 GB file

32K 7.3 GB · 128K 10.5 GB

Q5_K_S

GPT OSS 20B

14.8 GB11.7 GB file

32K 15.3 GB · 128K 17.0 GB

Qwen3.5 9B

7.2 GB6.4 GB file

32K 8.0 GB · 128K 11.2 GB

Q5_K_L

GPT OSS 20B

15.5 GB11.9 GB file

32K 16.0 GB · 128K 17.7 GB

Qwen3.5 9B

7.6 GB7.7 GB file

32K 8.4 GB · 128K 11.6 GB

BF16

GPT OSS 20B

42.2 GB~41.8 GB file

32K 42.7 GB · 128K 44.4 GB

Qwen3.5 9B

19.9 GB17.9 GB file

32K 20.7 GB · 128K 23.9 GB

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 →

Qwen3.5 9B

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Qwen3.5-9B-GGUF:Q4_K_M

All ways to run Qwen3.5 9B →

Specifications

Specifications of GPT OSS 20B and Qwen3.5 9B
Spec	GPT OSS 20B	Qwen3.5 9B
Publisher	OpenAI	Alibaba
Parameters	20.9B	9.7B
Active parameters	4.2B per token	—
Architecture	GptOssForCausalLM	Qwen3_5ForConditionalGeneration
Context	128K tokens	256K tokens
Modalities	Chat, Function-calling	Vision, Function-calling
License	Apache 2.0	Apache 2.0
Released	Aug 2025	Feb 2026

Frequently Asked Questions

Which is better, GPT OSS 20B or Qwen3.5 9B?

Qwen3.5 9B leads llmrun Score 99.4 to 96.2 (ranges overlap); both fit 24 GB at Q4_K_M; GPT OSS 20B is 1.8× faster on RTX 4090 (~190 vs ~103 tok/s). Choose GPT OSS 20B for 1.8× faster on RTX 4090 and also does chat; choose Qwen3.5 9B for higher llmrun Score and stronger at science.

Which needs less VRAM, GPT OSS 20B or Qwen3.5 9B?

At Q4_K_M, GPT OSS 20B requires 12.9 GB while Qwen3.5 9B needs 6.4 GB, making Qwen3.5 9B 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 103 tok/s for Qwen3.5 9B (Q4_K_M), so GPT OSS 20B is faster. Estimates, ±20%.

Can I run GPT OSS 20B or Qwen3.5 9B on a 16 GB GPU?

GPT OSS 20B fits at Q4_K_M; Qwen3.5 9B fits at Q4_K_M.

Which has a longer context window, GPT OSS 20B or Qwen3.5 9B?

GPT OSS 20B supports 131,072 tokens and Qwen3.5 9B supports 262,144 tokens.