Llama 4 Scout 17B 16E Instruct vs GPT OSS 120B

GPT OSS 120B leads llmrun Score 97.5 to 81.8; neither fits 24 GB.

Model A · Meta

Llama 4 Scout 17B 16E Instruct

81.8llmrun Score

108.6B · 17B active · Other · Apr 2025

Vision

Model B · OpenAI

GPT OSS 120B

97.5llmrun Score

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

ChatFunctions

Which should you choose?

Choose Llama 4 Scout 17B 16E Instruct if you want…

Also does vision
GPT OSS 120B doesn't list it

Choose GPT OSS 120B if you want…

Higher llmrun Score
97.5 vs 81.8
Stronger at science
103.4 vs 83.0
Stronger at reasoning
95.9 vs 79.7
Ahead on the benchmarks
8 of 8 shared boards
Also does chat, function-calling
Llama 4 Scout 17B 16E Instruct doesn't list it
More permissive license
Apache 2.0 vs Other

On your hardware

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

MemoryLlama 4 Scout 17B 16E InstructGPT OSS 120B

8 GB

RTX 4060 · 8 GB tier

Llama 4 Scout 17B 16E Instruct

Doesn't fit

smallest quant needs 38.2 GB

GPT OSS 120B

Doesn't fit

smallest quant needs 40.2 GB

12 GB

RTX 3060 12GB · 12 GB tier

Llama 4 Scout 17B 16E Instruct

Doesn't fit

smallest quant needs 38.2 GB

GPT OSS 120B

Doesn't fit

smallest quant needs 40.2 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Llama 4 Scout 17B 16E Instruct

Doesn't fit

smallest quant needs 38.2 GB

GPT OSS 120B

Doesn't fit

smallest quant needs 40.2 GB

24 GBreference

RTX 4090 · 24 GB tier

Llama 4 Scout 17B 16E Instruct

Doesn't fit

smallest quant needs 38.2 GB

GPT OSS 120B

Doesn't fit

smallest quant needs 40.2 GB

32 GB

RTX 5090 · 32 GB tier

Llama 4 Scout 17B 16E Instruct

Doesn't fit

smallest quant needs 38.2 GB

GPT OSS 120B

Doesn't fit

smallest quant needs 40.2 GB

48 GB

RTX A6000 · 48 GB tier

Llama 4 Scout 17B 16E Instruct

IQ2_M · ~65 tok/s

45.7 GB · up to 16K

GPT OSS 120B

IQ2_M · ~169 tok/s

40.2 GB · up to 128Kfaster

Mac 32 GB

Mac Mini M4 · Macs

Llama 4 Scout 17B 16E Instruct

Doesn't fit

smallest quant needs 38.2 GB

GPT OSS 120B

Doesn't fit

smallest quant needs 40.2 GB

Mac 64 GB

Mac Studio M4 Max · Macs

Llama 4 Scout 17B 16E Instruct

IQ3_M · ~32 tok/s

59.1 GB · up to 16K

GPT OSS 120B

Q4_0 · ~68 tok/s

59.1 GB · up to 64Kbetter quant

Mac 128 GB

Mac Studio M4 Max · Macs

Llama 4 Scout 17B 16E Instruct

Q4_K_M · ~26 tok/s

77 GB · up to 32K

GPT OSS 120B

Q4_K_M · ~61 tok/s

70.8 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

Llama 4 Scout 17B 16E Instruct GPT OSS 120B

Overall

Llama 4 Scout 17B 16E Instruct

81.878–86

GPT OSS 120B

97.595–100

Coding

Llama 4 Scout 17B 16E Instruct

no data

GPT OSS 120B

97.593–102

Agents

Llama 4 Scout 17B 16E Instruct

no data

GPT OSS 120B

81.574–89

Science

Llama 4 Scout 17B 16E Instruct

83.075–91

GPT OSS 120B

103.496–111

Reasoning

Llama 4 Scout 17B 16E Instruct

79.770–89

GPT OSS 120B

95.989–103

Llama 4 Scout 17B 16E Instruct · #79 of 100 open models · #40 of 60 that fit ≤96 GB

GPT OSS 120B · #58 of 100 open models · #25 of 60 that fit ≤96 GB

Benchmarks

8 shared boards: Llama 4 Scout 17B 16E Instruct leads 0, GPT OSS 120B leads 8 · Benchmarks imported Oct 2026

BoardLlama 4 Scout 17B 16E InstructGPT OSS 120B

GPQA Diamond

Llama 4 Scout 17B 16E Instruct

51.8%#51/98 open

IndependentEpoch AI · Apr 2025

GPT OSS 120B

75.8%#29/98 open

IndependentEpoch AI · Aug 2025

AIME 2024/2025

Llama 4 Scout 17B 16E Instruct

7.8%#62/86 open

IndependentEpoch AI · Apr 2025

GPT OSS 120B

88.9%#15/86 open

IndependentEpoch AI · Aug 2025

MMLU-Pro

Llama 4 Scout 17B 16E Instruct

74.3%#31/145 open

IndependentTIGER-Lab

GPT OSS 120B

80.8%#23/145 open

IndependentTIGER-Lab

SciCode

Llama 4 Scout 17B 16E Instruct

17.0%#63/66 open

Lab-reportedEpoch AI · Apr 2025

GPT OSS 120B

36.0%#43/66 open

Lab-reportedEpoch AI · Aug 2025

CritPt

Llama 4 Scout 17B 16E Instruct

0.0%#56/66 open

Lab-reportedEpoch AI · Apr 2025

GPT OSS 120B

1.1%#32/66 open

Lab-reportedEpoch AI · Aug 2025

DTBench

Llama 4 Scout 17B 16E Instruct

57.9%#53/68 open

Lab-reportedEpoch AI · Apr 2025

GPT OSS 120B

76.3%#27/68 open

Lab-reportedEpoch AI · Aug 2025

Fiction.LiveBench

Llama 4 Scout 17B 16E Instruct

36.0%#22/25 open

IndependentEpoch AI · Apr 2025

GPT OSS 120B

44.4%#20/25 open

IndependentEpoch AI · Aug 2025

LMCA

Llama 4 Scout 17B 16E Instruct

12.0%#46/54 open

Lab-reportedEpoch AI · Apr 2025

GPT OSS 120B

22.1%#32/54 open

Lab-reportedEpoch AI · Aug 2025

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

LMArena Text

Llama 4 Scout 17B 16E Instruct

1321.5#94/187 open

ArenaLMArena · Oct 2026

GPT OSS 120B

1351.8#75/187 open

ArenaLMArena · Oct 2026

Only Llama 4 Scout 17B 16E Instruct (4)

Only GPT OSS 120B (12)

VRAM by quantization

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

QuantLlama 4 Scout 17B 16E InstructGPT OSS 120B

Q2_K

Llama 4 Scout 17B 16E Instruct

50.8 GB39.6 GB file

32K 62.2 GB · 128K 98.7 GB

GPT OSS 120B

50.1 GB62.6 GB file

32K 50.8 GB · 128K 53.4 GB

Q3_K_S

Llama 4 Scout 17B 16E Instruct

52.3 GB46.7 GB file

32K 63.7 GB · 128K 100 GB

GPT OSS 120B

51.5 GB62.6 GB file

32K 52.3 GB · 128K 54.8 GB

Q3_K_M

Llama 4 Scout 17B 16E Instruct

58.3 GB51.8 GB file

32K 69.7 GB · 128K 106 GB

GPT OSS 120B

57.4 GB62.6 GB file

32K 58.1 GB · 128K 60.7 GB

Q4_0

Llama 4 Scout 17B 16E Instruct

59.8 GB61.2 GB file

32K 71.2 GB · 128K 108 GB

GPT OSS 120B

58.8 GB62.6 GB file

32K 59.6 GB · 128K 62.1 GB

Q4_K_M

Llama 4 Scout 17B 16E Instruct

71.7 GB65.4 GB file

32K 83.1 GB · 128K 120 GB

GPT OSS 120B

70.5 GB62.8 GB file

32K 71.3 GB · 128K 73.8 GB

Q5_K_M

Llama 4 Scout 17B 16E Instruct

85.2 GB76.5 GB file

32K 96.6 GB · 128K 133 GB

GPT OSS 120B

83.7 GB62.9 GB file

32K 84.4 GB · 128K 86.9 GB

Q6_K

Llama 4 Scout 17B 16E Instruct

98.6 GB88.4 GB file

32K 110 GB · 128K 147 GB

GPT OSS 120B

96.8 GB63.3 GB file

32K 97.5 GB · 128K 100 GB

Q8_0

Llama 4 Scout 17B 16E Instruct

120 GB114.5 GB file

32K 131 GB · 128K 167 GB

GPT OSS 120B

117 GB~116.8 GB file

32K 118 GB · 128K 121 GB

17 more quants

IQ2_XXS

Llama 4 Scout 17B 16E Instruct

32.9 GB37.4 GB file

32K 44.3 GB · 128K 80.8 GB

GPT OSS 120B

not listed

IQ2_XS

Llama 4 Scout 17B 16E Instruct

35.9 GB31.8 GB file

32K 47.3 GB · 128K 83.8 GB

GPT OSS 120B

not listed

IQ2_S

Llama 4 Scout 17B 16E Instruct

37.4 GB32.3 GB file

32K 48.8 GB · 128K 85.3 GB

GPT OSS 120B

not listed

IQ2_M

Llama 4 Scout 17B 16E Instruct

40.3 GB39.1 GB file

32K 51.8 GB · 128K 88.3 GB

GPT OSS 120B

39.8 GB~39.4 GB file

32K 40.6 GB · 128K 43.1 GB

IQ3_XXS

Llama 4 Scout 17B 16E Instruct

46.3 GB45.7 GB file

32K 57.7 GB · 128K 94.3 GB

GPT OSS 120B

not listed

Q2_K_S

Llama 4 Scout 17B 16E Instruct

47.8 GB37.0 GB file

32K 59.2 GB · 128K 95.8 GB

GPT OSS 120B

not listed

IQ3_XS

Llama 4 Scout 17B 16E Instruct

49.3 GB44.3 GB file

32K 60.7 GB · 128K 97.3 GB

GPT OSS 120B

not listed

IQ3_S

Llama 4 Scout 17B 16E Instruct

50.8 GB46.8 GB file

32K 62.2 GB · 128K 98.7 GB

GPT OSS 120B

not listed

IQ3_M

Llama 4 Scout 17B 16E Instruct

53.8 GB47.5 GB file

32K 65.2 GB · 128K 102 GB

GPT OSS 120B

53.0 GB62.7 GB file

32K 53.7 GB · 128K 56.3 GB

Q3_K_L

Llama 4 Scout 17B 16E Instruct

61.3 GB57.8 GB file

32K 72.7 GB · 128K 109 GB

GPT OSS 120B

60.3 GB62.6 GB file

32K 61.0 GB · 128K 63.6 GB

IQ4_XS

Llama 4 Scout 17B 16E Instruct

64.2 GB57.7 GB file

32K 75.7 GB · 128K 112 GB

GPT OSS 120B

63.2 GB62.7 GB file

32K 64.0 GB · 128K 66.5 GB

IQ4_NL

Llama 4 Scout 17B 16E Instruct

67.2 GB60.9 GB file

32K 78.6 GB · 128K 115 GB

GPT OSS 120B

66.1 GB62.7 GB file

32K 66.9 GB · 128K 69.4 GB

Q4_1

Llama 4 Scout 17B 16E Instruct

67.2 GB67.6 GB file

32K 78.6 GB · 128K 115 GB

GPT OSS 120B

66.1 GB62.7 GB file

32K 66.9 GB · 128K 69.4 GB

Q4_K_S

Llama 4 Scout 17B 16E Instruct

67.2 GB61.5 GB file

32K 78.6 GB · 128K 115 GB

GPT OSS 120B

66.1 GB62.8 GB file

32K 66.9 GB · 128K 69.4 GB

Q4_K_L

Llama 4 Scout 17B 16E Instruct

not listed

GPT OSS 120B

72.0 GB63.1 GB file

32K 72.7 GB · 128K 75.3 GB

Q5_K_S

Llama 4 Scout 17B 16E Instruct

82.2 GB74.3 GB file

32K 93.6 GB · 128K 130 GB

GPT OSS 120B

80.7 GB62.9 GB file

32K 81.5 GB · 128K 84.0 GB

BF16

Llama 4 Scout 17B 16E Instruct

239 GB215.6 GB file

32K 250 GB · 128K 287 GB

GPT OSS 120B

234 GB~233.7 GB file

32K 235 GB · 128K 237 GB

How to run each

Llama 4 Scout 17B 16E Instruct

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF:Q4_K_M

All ways to run Llama 4 Scout 17B 16E Instruct →

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 →

Specifications

Specifications of Llama 4 Scout 17B 16E Instruct and GPT OSS 120B
Spec	Llama 4 Scout 17B 16E Instruct	GPT OSS 120B
Publisher	Meta	OpenAI
Parameters	108.6B	116.8B
Active parameters	17B per token	5.8B per token
Architecture	—	GptOssForCausalLM
Context	—	128K tokens
Modalities	Vision	Chat, Function-calling
License	Other	Apache 2.0
Released	Apr 2025	Aug 2025

Frequently Asked Questions

Which is better, Llama 4 Scout 17B 16E Instruct or GPT OSS 120B?

GPT OSS 120B leads llmrun Score 97.5 to 81.8; neither fits 24 GB. Choose Llama 4 Scout 17B 16E Instruct for also does vision; choose GPT OSS 120B for higher llmrun Score and stronger at science.

Which needs less VRAM, Llama 4 Scout 17B 16E Instruct or GPT OSS 120B?

At Q4_K_M, Llama 4 Scout 17B 16E Instruct requires 71.7 GB while GPT OSS 120B needs 70.5 GB, making GPT OSS 120B the easier model to run on your local setup.

Can I run Llama 4 Scout 17B 16E Instruct or GPT OSS 120B on a 16 GB GPU?

Llama 4 Scout 17B 16E Instruct does not fit (smallest quant needs 38.2 GB); GPT OSS 120B does not fit (smallest quant needs 40.2 GB).