GPT OSS 20B vs Qwen3.5 35B A3B

Qwen3.5 35B A3B leads llmrun Score 105.8 to 96.4; both fit 24 GB at Q4_K_M; GPT OSS 20B is 1.3× faster on RTX 4090 (~190 vs ~151 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

Qwen3.5 35B A3B

105.8llmrun Score

36.0B · 4.7B active · 256K context · Apache 2.0 · Feb 2026

Vision

Which should you choose?

Choose GPT OSS 20B if you want…

Fits a 12 GB GPU
IQ4_XS · 11.8 GB; Qwen3.5 35B A3B needs 15.7 GB at its smallest quant
1.3× faster on RTX 4090
~190 vs ~151 tok/s
Lighter on memory
12.9 vs 22.0 GB at Q4_K_M
Also does chat, function-calling
Qwen3.5 35B A3B doesn't list it

Choose Qwen3.5 35B A3B if you want…

Higher llmrun Score
105.8 vs 96.4
Stronger at reasoning
106.7 vs 91.3
Stronger at science
107.6 vs 93.1
Ahead on the benchmarks
5 of 7 shared boards
Longer context window
256K vs 128K tokens
Also does vision
GPT OSS 20B doesn't list it

On your hardware

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

MemoryGPT OSS 20BQwen3.5 35B A3B

8 GB

RTX 4060 · 8 GB tier

GPT OSS 20B

IQ2_M · ~103 tok/s

7.6 GB · up to 32Kfits

Qwen3.5 35B A3B

Doesn't fit

smallest quant needs 15.7 GB

12 GB

RTX 3060 12GB · 12 GB tier

GPT OSS 20B

IQ4_XS · ~89 tok/s

11.8 GB · up to 16Kfits

Qwen3.5 35B A3B

Doesn't fit

smallest quant needs 15.7 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

Qwen3.5 35B A3B

Q2_K · ~108 tok/s

15.7 GB · up to 32K

24 GBreference

RTX 4090 · 24 GB tier

GPT OSS 20B

Q4_K_M · ~190 tok/s

13.1 GB · up to 128Kfaster

Qwen3.5 35B A3B

Q4_K_M · ~151 tok/s

22 GB · up to 128K

32 GB

RTX 5090 · 32 GB tier

GPT OSS 20B

Q4_K_M · ~282 tok/s

13.1 GB · up to 128Kfaster

Qwen3.5 35B A3B

Q4_K_M · ~213 tok/s

22 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 35B A3B

Q4_K_M · ~125 tok/s

22 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 35B A3B

Q4_K_M · ~24 tok/s

22 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 35B A3B

Q4_K_M · ~64 tok/s

22 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 35B A3B

Q4_K_M · ~64 tok/s

22 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 35B A3B

Overall

GPT OSS 20B

96.493–100

Qwen3.5 35B A3B

105.8102–110

Coding

GPT OSS 20B

101.993–111

Qwen3.5 35B A3B

no data

Science

GPT OSS 20B

93.186–101

Qwen3.5 35B A3B

107.699–116

Reasoning

GPT OSS 20B

91.383–100

Qwen3.5 35B A3B

106.798–116

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

Qwen3.5 35B A3B · #44 of 106 open models · #6 of 36 that fit 24 GB

Benchmarks

7 shared boards: GPT OSS 20B leads 2, Qwen3.5 35B A3B leads 5 · Benchmarks imported Nov 2026

BoardGPT OSS 20BQwen3.5 35B A3B

GPQA Diamond

GPT OSS 20B

60.8%#44/100 open

IndependentEpoch AI · Aug 2025

Qwen3.5 35B A3B

83.5%#25/100 open

IndependentEpoch AI · Feb 2026

AIME 2024/2025

GPT OSS 20B

65.3%#36/88 open

IndependentEpoch AI · Aug 2025

Qwen3.5 35B A3B

70.0%#31/88 open

IndependentEpoch AI · Feb 2026

MMLU-Pro

GPT OSS 20B

73.6%#33/146 open

IndependentTIGER-Lab

Qwen3.5 35B A3B

85.3%#7/146 open

IndependentTIGER-Lab

SciCode

GPT OSS 20B

38.9%#41/72 open

Lab-reportedEpoch AI · Aug 2025

Qwen3.5 35B A3B

29.3%#60/72 open

Lab-reportedEpoch AI · Feb 2026

CritPt

GPT OSS 20B

1.4%#36/84 open

Lab-reportedEpoch AI · Aug 2025

Qwen3.5 35B A3B

0.6%#45/84 open

Lab-reportedEpoch AI · Feb 2026

DTBench

GPT OSS 20B

68.0%#36/70 open

Lab-reportedEpoch AI · Aug 2025

Qwen3.5 35B A3B

80.0%#24/70 open

Lab-reportedEpoch AI · Feb 2026

LMCA

GPT OSS 20B

14.5%#45/56 open

Lab-reportedEpoch AI · Aug 2025

Qwen3.5 35B A3B

29.5%#23/56 open

Lab-reportedEpoch AI · Feb 2026

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

LMArena Text

GPT OSS 20B

1317.3#98/188 open

ArenaLMArena · Oct 2026

Qwen3.5 35B A3B

1393.8#55/188 open

ArenaLMArena · Oct 2026

Only GPT OSS 20B (3)

Only Qwen3.5 35B A3B (1)

LMArena WebDev1254.2

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 35B A3B

Q2_K

GPT OSS 20B

9.3 GB11.5 GB file

32K 9.8 GB · 128K 11.5 GB

Qwen3.5 35B A3B

15.7 GB~15.3 GB file

32K 15.9 GB · 128K 16.9 GB

Q3_K_S

GPT OSS 20B

9.5 GB11.5 GB file

32K 10.0 GB · 128K 11.7 GB

Qwen3.5 35B A3B

not listed

Q3_K_M

GPT OSS 20B

10.6 GB11.5 GB file

32K 11.1 GB · 128K 12.8 GB

Qwen3.5 35B A3B

17.9 GB~17.5 GB file

32K 18.2 GB · 128K 19.2 GB

Q4_0

GPT OSS 20B

10.8 GB11.5 GB file

32K 11.3 GB · 128K 13.0 GB

Qwen3.5 35B A3B

not listed

Q4_K_M

GPT OSS 20B

12.9 GB11.6 GB file

32K 13.4 GB · 128K 15.1 GB

Qwen3.5 35B A3B

22.0 GB~21.6 GB file

32K 22.2 GB · 128K 23.2 GB

Q5_K_M

GPT OSS 20B

15.3 GB11.7 GB file

32K 15.8 GB · 128K 17.5 GB

Qwen3.5 35B A3B

26.0 GB~25.6 GB file

32K 26.3 GB · 128K 27.3 GB

Q6_K

GPT OSS 20B

17.6 GB12.0 GB file

32K 18.1 GB · 128K 19.8 GB

Qwen3.5 35B A3B

30.0 GB~29.7 GB file

32K 30.3 GB · 128K 31.3 GB

Q8_0

GPT OSS 20B

21.3 GB~20.9 GB file

32K 21.8 GB · 128K 23.5 GB

Qwen3.5 35B A3B

36.3 GB~36.0 GB file

32K 36.6 GB · 128K 37.6 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 35B A3B

not listed

IQ2_XS

GPT OSS 20B

6.7 GB~6.3 GB file

32K 7.2 GB · 128K 8.9 GB

Qwen3.5 35B A3B

not listed

IQ2_S

GPT OSS 20B

6.9 GB~6.5 GB file

32K 7.4 GB · 128K 9.1 GB

Qwen3.5 35B A3B

not listed

IQ2_M

GPT OSS 20B

7.4 GB~7.1 GB file

32K 7.9 GB · 128K 9.6 GB

Qwen3.5 35B A3B

not listed

IQ3_XXS

GPT OSS 20B

8.5 GB11.6 GB file

32K 9.0 GB · 128K 10.7 GB

Qwen3.5 35B A3B

not listed

Q2_K_S

GPT OSS 20B

8.7 GB12.1 GB file

32K 9.2 GB · 128K 10.9 GB

Qwen3.5 35B A3B

not listed

IQ3_XS

GPT OSS 20B

9.0 GB11.6 GB file

32K 9.5 GB · 128K 11.2 GB

Qwen3.5 35B A3B

not listed

IQ3_S

GPT OSS 20B

9.3 GB12.1 GB file

32K 9.8 GB · 128K 11.5 GB

Qwen3.5 35B A3B

not listed

IQ3_M

GPT OSS 20B

9.8 GB11.6 GB file

32K 10.3 GB · 128K 12.0 GB

Qwen3.5 35B A3B

not listed

Q3_K_L

GPT OSS 20B

11.1 GB11.5 GB file

32K 11.6 GB · 128K 13.3 GB

Qwen3.5 35B A3B

not listed

IQ4_XS

GPT OSS 20B

11.6 GB11.6 GB file

32K 12.1 GB · 128K 13.8 GB

Qwen3.5 35B A3B

not listed

IQ4_NL

GPT OSS 20B

12.1 GB11.6 GB file

32K 12.6 GB · 128K 14.3 GB

Qwen3.5 35B A3B

not listed

Q4_1

GPT OSS 20B

12.1 GB11.6 GB file

32K 12.6 GB · 128K 14.3 GB

Qwen3.5 35B A3B

not listed

Q4_K_S

GPT OSS 20B

12.1 GB11.6 GB file

32K 12.6 GB · 128K 14.3 GB

Qwen3.5 35B A3B

not listed

Q4_K_L

GPT OSS 20B

13.2 GB11.9 GB file

32K 13.7 GB · 128K 15.4 GB

Qwen3.5 35B A3B

not listed

Q5_K_S

GPT OSS 20B

14.8 GB11.7 GB file

32K 15.3 GB · 128K 17.0 GB

Qwen3.5 35B A3B

not listed

Q5_K_L

GPT OSS 20B

15.5 GB11.9 GB file

32K 16.0 GB · 128K 17.7 GB

Qwen3.5 35B A3B

not listed

BF16

GPT OSS 20B

42.2 GB~41.8 GB file

32K 42.7 GB · 128K 44.4 GB

Qwen3.5 35B A3B

72.3 GB~71.9 GB file

32K 72.5 GB · 128K 73.6 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 35B A3B

No local recipe · Q4_K_M

No GGUF repo entry exists for this model yet.

All ways to run Qwen3.5 35B A3B →

Specifications

Specifications of GPT OSS 20B and Qwen3.5 35B A3B
Spec	GPT OSS 20B	Qwen3.5 35B A3B
Publisher	OpenAI	Alibaba
Parameters	20.9B	36.0B
Active parameters	4.2B per token	4.7B per token
Architecture	GptOssForCausalLM	Qwen3_5MoeForConditionalGeneration
Context	128K tokens	256K tokens
Modalities	Chat, Function-calling	Vision
License	Apache 2.0	Apache 2.0
Released	Aug 2025	Feb 2026

Frequently Asked Questions

Which is better, GPT OSS 20B or Qwen3.5 35B A3B?

Qwen3.5 35B A3B leads llmrun Score 105.8 to 96.4; both fit 24 GB at Q4_K_M; GPT OSS 20B is 1.3× faster on RTX 4090 (~190 vs ~151 tok/s). Choose GPT OSS 20B for fits a 12 GB GPU and 1.3× faster on RTX 4090; choose Qwen3.5 35B A3B for higher llmrun Score and stronger at reasoning.

Which needs less VRAM, GPT OSS 20B or Qwen3.5 35B A3B?

At Q4_K_M, GPT OSS 20B requires 12.9 GB while Qwen3.5 35B A3B needs 22.0 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 151 tok/s for Qwen3.5 35B A3B (Q4_K_M), so GPT OSS 20B is faster. Estimates, ±20%.

Can I run GPT OSS 20B or Qwen3.5 35B A3B on a 16 GB GPU?

GPT OSS 20B fits at Q4_K_M; Qwen3.5 35B A3B fits at Q2_K.

Which has a longer context window, GPT OSS 20B or Qwen3.5 35B A3B?

GPT OSS 20B supports 131,072 tokens and Qwen3.5 35B A3B supports 262,144 tokens.