GPT OSS 120B vs Qwen3.8 27B

Qwen3.8 27B leads llmrun Score 121.5 to 97.6; only Qwen3.8 27B fits 24 GB (Q4_K_M); GPT OSS 120B needs 40.2 GB even at its smallest quant.

Model A · OpenAI

GPT OSS 120B

97.6llmrun Score

116.8B · 5.8B active · 128K context · Apache 2.0 · Aug 2025

ChatFunctions

Model B · Alibaba

Qwen3.8 27B

121.5llmrun Score

27.8B · 256K context · Apache 2.0 · Aug 2026

VisionFunctions

Which should you choose?

Choose GPT OSS 120B if you want…

Also does chat
Qwen3.8 27B doesn't list it

Choose Qwen3.8 27B if you want…

Higher llmrun Score
121.5 vs 97.6
Stronger at reasoning
124.1 vs 96.9
Stronger at coding
112.1 vs 97.5
Ahead on the benchmarks
5 of 5 shared boards
Fits a 12 GB GPU
IQ3_XXS · 12 GB; GPT OSS 120B needs 40.2 GB at its smallest quant
Fits a Mac 32 GB
Q4_K_M · 17.9 GB; GPT OSS 120B needs 40.2 GB at its smallest quant

On your hardware

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

MemoryGPT OSS 120BQwen3.8 27B

8 GB

RTX 4060 · 8 GB tier

GPT OSS 120B

Doesn't fit

smallest quant needs 40.2 GB

Qwen3.8 27B

Doesn't fit

smallest quant needs 8.8 GB

12 GB

RTX 3060 12GB · 12 GB tier

GPT OSS 120B

Doesn't fit

smallest quant needs 40.2 GB

Qwen3.8 27B

IQ3_XXS · ~20 tok/s

12 GB · up to 16Kfits

16 GB

RTX 5060 Ti 16GB · 16 GB tier

GPT OSS 120B

Doesn't fit

smallest quant needs 40.2 GB

Qwen3.8 27B

Q3_K_L · ~19 tok/s

15.4 GB · up to 16Kfits

24 GBreference

RTX 4090 · 24 GB tier

GPT OSS 120B

Doesn't fit

smallest quant needs 40.2 GB

Qwen3.8 27B

Q4_K_M · ~38 tok/s

17.9 GB · up to 64Kfits

32 GB

RTX 5090 · 32 GB tier

GPT OSS 120B

Doesn't fit

smallest quant needs 40.2 GB

Qwen3.8 27B

Q4_K_M · ~67 tok/s

17.9 GB · up to 256Kfits

48 GB

RTX A6000 · 48 GB tier

GPT OSS 120B

IQ2_M · ~169 tok/s

40.2 GB · up to 128K

Qwen3.8 27B

Q4_K_M · ~29 tok/s

17.9 GB · up to 256Kmore headroom

Mac 32 GB

Mac Mini M4 · Macs

GPT OSS 120B

Doesn't fit

smallest quant needs 40.2 GB

Qwen3.8 27B

Q4_K_M · ~5 tok/s

17.9 GB · up to 128Kfits

Mac 64 GB

Mac Studio M4 Max · Macs

GPT OSS 120B

Q4_0 · ~68 tok/s

59.1 GB · up to 64K

Qwen3.8 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256Kmore headroom

Mac 128 GB

Mac Studio M4 Max · Macs

GPT OSS 120B

Q4_K_M · ~61 tok/s

70.8 GB · up to 128Kfaster

Qwen3.8 27B

Q4_K_M · ~22 tok/s

17.9 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 120B Qwen3.8 27B

Overall

GPT OSS 120B

97.695–100

Qwen3.8 27B

121.5119–124

Coding

GPT OSS 120B

97.593–102

Qwen3.8 27B

112.1105–119

Agents

GPT OSS 120B

81.574–89

Qwen3.8 27B

no data

Math

GPT OSS 120B

no data

Qwen3.8 27B

117.5111–125

Science

GPT OSS 120B

103.496–111

Qwen3.8 27B

112.093–131

Reasoning

GPT OSS 120B

96.990–104

Qwen3.8 27B

124.1121–127

GPT OSS 120B · #54 of 92 open models · #23 of 54 that fit ≤96 GB

Qwen3.8 27B · #10 of 92 open models · #1 of 34 that fit 24 GB

Benchmarks

5 shared boards: GPT OSS 120B leads 0, Qwen3.8 27B leads 5 · Benchmarks imported Oct 2026

BoardGPT OSS 120BQwen3.8 27B

LMArena Text

GPT OSS 120B

1351.8#74/186 open

ArenaLMArena · Oct 2026

Qwen3.8 27B

1438.1#22/186 open

ArenaLMArena · Oct 2026

SciCode

GPT OSS 120B

36.0%#39/65 open

Lab-reportedEpoch AI · Aug 2025

Qwen3.8 27B

46.6%#19/65 open

Lab-reportedEpoch AI · Aug 2026

CritPt

GPT OSS 120B

1.1%#31/65 open

Lab-reportedEpoch AI · Aug 2025

Qwen3.8 27B

5.4%#15/65 open

Lab-reportedEpoch AI · Aug 2026

DTBench

GPT OSS 120B

76.3%#27/68 open

Lab-reportedEpoch AI · Aug 2025

Qwen3.8 27B

88.0%#9/68 open

Lab-reportedEpoch AI · Aug 2026

LMCA

GPT OSS 120B

22.1%#32/54 open

Lab-reportedEpoch AI · Aug 2025

Qwen3.8 27B

41.4%#7/54 open

Lab-reportedEpoch AI · Aug 2026

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

APEX-Agents

GPT OSS 120B

4.4%#16/16 open

Lab-reportedEpoch AI · Aug 2025

Qwen3.8 27B

47.5%#5/16 open

Lab-reportedEpoch AI · Aug 2026

Surface Evolver Bench

GPT OSS 120B

25.0%#11/13 open

Lab-reportedEpoch AI · Aug 2025

Qwen3.8 27B

45.0%#7/13 open

Lab-reportedEpoch AI · Aug 2026

Only GPT OSS 120B (14)

Only Qwen3.8 27B (7)

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 120BQwen3.8 27B

Q2_K

GPT OSS 120B

50.1 GB62.6 GB file

32K 50.8 GB · 128K 53.4 GB

Qwen3.8 27B

12.6 GB10.8 GB file

32K 13.9 GB · 128K 19.3 GB

Q3_K_S

GPT OSS 120B

51.5 GB62.6 GB file

32K 52.3 GB · 128K 54.8 GB

Qwen3.8 27B

12.9 GB12.7 GB file

32K 14.2 GB · 128K 19.6 GB

Q3_K_M

GPT OSS 120B

57.4 GB62.6 GB file

32K 58.1 GB · 128K 60.7 GB

Qwen3.8 27B

14.3 GB13.4 GB file

32K 15.6 GB · 128K 21.0 GB

Q4_0

GPT OSS 120B

58.8 GB62.6 GB file

32K 59.6 GB · 128K 62.1 GB

Qwen3.8 27B

14.6 GB~13.9 GB file

32K 16.0 GB · 128K 21.4 GB

Q4_K_M

GPT OSS 120B

70.5 GB62.8 GB file

32K 71.3 GB · 128K 73.8 GB

Qwen3.8 27B

17.4 GB16.5 GB file

32K 18.8 GB · 128K 24.1 GB

Q5_K_M

GPT OSS 120B

83.7 GB62.9 GB file

32K 84.4 GB · 128K 86.9 GB

Qwen3.8 27B

20.5 GB19.8 GB file

32K 21.9 GB · 128K 27.3 GB

Q6_K

GPT OSS 120B

96.8 GB63.3 GB file

32K 97.5 GB · 128K 100 GB

Qwen3.8 27B

23.7 GB22.0 GB file

32K 25.0 GB · 128K 30.4 GB

Q8_0

GPT OSS 120B

117 GB~116.8 GB file

32K 118 GB · 128K 121 GB

Qwen3.8 27B

28.5 GB29.0 GB file

32K 29.9 GB · 128K 35.2 GB

17 more quants

IQ2_XXS

GPT OSS 120B

not listed

Qwen3.8 27B

8.4 GB7.3 GB file

32K 9.7 GB · 128K 15.1 GB

IQ2_XS

GPT OSS 120B

not listed

Qwen3.8 27B

9.1 GB9.1 GB file

32K 10.4 GB · 128K 15.8 GB

IQ2_S

GPT OSS 120B

not listed

Qwen3.8 27B

9.4 GB8.4 GB file

32K 10.8 GB · 128K 16.1 GB

IQ2_M

GPT OSS 120B

39.8 GB~39.4 GB file

32K 40.6 GB · 128K 43.1 GB

Qwen3.8 27B

10.1 GB10.5 GB file

32K 11.5 GB · 128K 16.8 GB

IQ3_XXS

GPT OSS 120B

not listed

Qwen3.8 27B

11.5 GB10.9 GB file

32K 12.9 GB · 128K 18.2 GB

IQ3_XS

GPT OSS 120B

not listed

Qwen3.8 27B

12.2 GB10.4 GB file

32K 13.6 GB · 128K 18.9 GB

IQ3_S

GPT OSS 120B

not listed

Qwen3.8 27B

12.6 GB12.0 GB file

32K 13.9 GB · 128K 19.3 GB

IQ3_M

GPT OSS 120B

53.0 GB62.7 GB file

32K 53.7 GB · 128K 56.3 GB

Qwen3.8 27B

13.3 GB14.9 GB file

32K 14.6 GB · 128K 20.0 GB

Q3_K_L

GPT OSS 120B

60.3 GB62.6 GB file

32K 61.0 GB · 128K 63.6 GB

Qwen3.8 27B

15.0 GB14.1 GB file

32K 16.3 GB · 128K 21.7 GB

IQ4_XS

GPT OSS 120B

63.2 GB62.7 GB file

32K 64.0 GB · 128K 66.5 GB

Qwen3.8 27B

15.7 GB14.3 GB file

32K 17.0 GB · 128K 22.4 GB

IQ4_NL

GPT OSS 120B

66.1 GB62.7 GB file

32K 66.9 GB · 128K 69.4 GB

Qwen3.8 27B

16.4 GB17.4 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_1

GPT OSS 120B

66.1 GB62.7 GB file

32K 66.9 GB · 128K 69.4 GB

Qwen3.8 27B

16.4 GB17.5 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_K_S

GPT OSS 120B

66.1 GB62.8 GB file

32K 66.9 GB · 128K 69.4 GB

Qwen3.8 27B

16.4 GB15.4 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_K_L

GPT OSS 120B

72.0 GB63.1 GB file

32K 72.7 GB · 128K 75.3 GB

Qwen3.8 27B

17.8 GB18.8 GB file

32K 19.1 GB · 128K 24.5 GB

Q5_K_S

GPT OSS 120B

80.7 GB62.9 GB file

32K 81.5 GB · 128K 84.0 GB

Qwen3.8 27B

19.9 GB18.7 GB file

32K 21.2 GB · 128K 26.6 GB

Q5_K_L

GPT OSS 120B

not listed

Qwen3.8 27B

20.9 GB21.5 GB file

32K 22.2 GB · 128K 27.6 GB

BF16

GPT OSS 120B

234 GB~233.7 GB file

32K 235 GB · 128K 237 GB

Qwen3.8 27B

56.3 GB54.7 GB file

32K 57.7 GB · 128K 63.0 GB

How to run each

GPT OSS 120B

Ollama · Q4_K_M

$ollama run hf.co/unsloth/gpt-oss-120b-GGUF:Q4_K_M

All ways to run GPT OSS 120B →

Qwen3.8 27B

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Qwen3.8-27B-GGUF:Q4_K_M

All ways to run Qwen3.8 27B →

Specifications

Specifications of GPT OSS 120B and Qwen3.8 27B
Spec	GPT OSS 120B	Qwen3.8 27B
Publisher	OpenAI	Alibaba
Parameters	116.8B	27.8B
Active parameters	5.8B 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	Aug 2026

Frequently Asked Questions

Which is better, GPT OSS 120B or Qwen3.8 27B?

Qwen3.8 27B leads llmrun Score 121.5 to 97.6; only Qwen3.8 27B fits 24 GB (Q4_K_M); GPT OSS 120B needs 40.2 GB even at its smallest quant. Choose GPT OSS 120B for also does chat; choose Qwen3.8 27B for higher llmrun Score and stronger at reasoning.

Which needs less VRAM, GPT OSS 120B or Qwen3.8 27B?

At Q4_K_M, GPT OSS 120B requires 70.5 GB while Qwen3.8 27B needs 17.4 GB, making Qwen3.8 27B the easier model to run on your local setup.

Can I run GPT OSS 120B or Qwen3.8 27B on a 16 GB GPU?

GPT OSS 120B does not fit (smallest quant needs 40.2 GB); Qwen3.8 27B fits at Q3_K_L.

Which has a longer context window, GPT OSS 120B or Qwen3.8 27B?

GPT OSS 120B supports 131,072 tokens and Qwen3.8 27B supports 262,144 tokens.