GPT OSS 120B vs GLM 4.5 Air

GPT OSS 120B and GLM 4.5 Air match in llmrun Score, with values of 97.6 versus 96.3; neither fits 24 GB.

Model A · OpenAI

GPT OSS 120B

97.6llmrun Score

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

ChatFunctions

Model B · Z.ai

GLM 4.5 Air

96.3llmrun Score

110.5B · 15B active · 128K context · MIT · Jul 2025

ChatFunctions

Which should you choose?

Choose GLM 4.5 Air if you want…

Fits a 48 GB GPU
IQ3_XS · 46.9 GB; GPT OSS 120B needs 40.2 GB at its smallest quant

GPT OSS 120B: no clear edge over GLM 4.5 Air 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 120BGLM 4.5 Air

8 GB

RTX 4060 · 8 GB tier

GPT OSS 120B

Doesn't fit

smallest quant needs 40.2 GB

GLM 4.5 Air

Doesn't fit

smallest quant needs 31.7 GB

12 GB

RTX 3060 12GB · 12 GB tier

GPT OSS 120B

Doesn't fit

smallest quant needs 40.2 GB

GLM 4.5 Air

Doesn't fit

smallest quant needs 31.7 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

GPT OSS 120B

Doesn't fit

smallest quant needs 40.2 GB

GLM 4.5 Air

Doesn't fit

smallest quant needs 31.7 GB

24 GBreference

RTX 4090 · 24 GB tier

GPT OSS 120B

Doesn't fit

smallest quant needs 40.2 GB

GLM 4.5 Air

Doesn't fit

smallest quant needs 31.7 GB

32 GB

RTX 5090 · 32 GB tier

GPT OSS 120B

Doesn't fit

smallest quant needs 40.2 GB

GLM 4.5 Air

IQ2_XXS · ~164 tok/s

31.7 GB · up to 16Kfits

48 GB

RTX A6000 · 48 GB tier

GPT OSS 120B

IQ2_M · ~169 tok/s

40.2 GB · up to 128K

GLM 4.5 Air

IQ3_XS · ~67 tok/s

46.9 GB · up to 32Kbetter quant

Mac 32 GB

Mac Mini M4 · Macs

GPT OSS 120B

Doesn't fit

smallest quant needs 40.2 GB

GLM 4.5 Air

Doesn't fit

smallest quant needs 31.7 GB

Mac 64 GB

Mac Studio M4 Max · Macs

GPT OSS 120B

Q4_0 · ~68 tok/s

59.1 GB · up to 64Kbetter quant

GLM 4.5 Air

Q3_K_L · ~34 tok/s

57.9 GB · up to 32K

Mac 128 GB

Mac Studio M4 Max · Macs

GPT OSS 120B

Q4_K_M · ~61 tok/s

70.8 GB · up to 128Kfaster

GLM 4.5 Air

Q4_K_M · ~30 tok/s

67.6 GB · up to 128K

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 GLM 4.5 Air

Overall

GPT OSS 120B

97.695–100

GLM 4.5 Air

96.386–107

Coding

GPT OSS 120B

97.593–102

GLM 4.5 Air

no data

Agents

GPT OSS 120B

81.574–89

GLM 4.5 Air

no data

Science

GPT OSS 120B

103.496–111

GLM 4.5 Air

no data

Reasoning

GPT OSS 120B

96.990–104

GLM 4.5 Air

no data

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

GLM 4.5 Air · #57 of 92 open models · #26 of 54 that fit ≤96 GB

Benchmarks

2 shared boards: GPT OSS 120B leads 0, GLM 4.5 Air leads 2 · Benchmarks imported Oct 2026

BoardGPT OSS 120BGLM 4.5 Air

LMArena Text

GPT OSS 120B

1351.8#74/186 open

ArenaLMArena · Oct 2026

GLM 4.5 Air

1373.1#62/186 open

ArenaLMArena · Oct 2026

MMLU-Pro

GPT OSS 120B

80.8%#23/144 open

IndependentTIGER-Lab

GLM 4.5 Air

81.4%#19/144 open

IndependentTIGER-Lab

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

Only GPT OSS 120B (19)

Only GLM 4.5 Air (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 120BGLM 4.5 Air

Q2_K

GPT OSS 120B

50.1 GB62.6 GB file

32K 50.8 GB · 128K 53.4 GB

GLM 4.5 Air

47.4 GB45.3 GB file

32K 49.3 GB · 128K 55.5 GB

Q3_K_S

GPT OSS 120B

51.5 GB62.6 GB file

32K 52.3 GB · 128K 54.8 GB

GLM 4.5 Air

48.8 GB52.7 GB file

32K 50.7 GB · 128K 56.9 GB

Q3_K_M

GPT OSS 120B

57.4 GB62.6 GB file

32K 58.1 GB · 128K 60.7 GB

GLM 4.5 Air

54.3 GB57.2 GB file

32K 56.2 GB · 128K 62.4 GB

Q4_0

GPT OSS 120B

58.8 GB62.6 GB file

32K 59.6 GB · 128K 62.1 GB

GLM 4.5 Air

55.7 GB62.8 GB file

32K 57.6 GB · 128K 63.8 GB

Q4_K_M

GPT OSS 120B

70.5 GB62.8 GB file

32K 71.3 GB · 128K 73.8 GB

GLM 4.5 Air

66.7 GB73.0 GB file

32K 68.6 GB · 128K 74.8 GB

Q5_K_M

GPT OSS 120B

83.7 GB62.9 GB file

32K 84.4 GB · 128K 86.9 GB

GLM 4.5 Air

79.1 GB83.5 GB file

32K 81.1 GB · 128K 87.2 GB

Q6_K

GPT OSS 120B

96.8 GB63.3 GB file

32K 97.5 GB · 128K 100 GB

GLM 4.5 Air

91.6 GB99.0 GB file

32K 93.5 GB · 128K 99.7 GB

Q8_0

GPT OSS 120B

117 GB~116.8 GB file

32K 118 GB · 128K 121 GB

GLM 4.5 Air

111 GB117.5 GB file

32K 113 GB · 128K 119 GB

15 more quants

IQ2_XXS

GPT OSS 120B

not listed

GLM 4.5 Air

30.8 GB42.7 GB file

32K 32.7 GB · 128K 38.9 GB

IQ2_XS

GPT OSS 120B

not listed

GLM 4.5 Air

33.6 GB42.2 GB file

32K 35.5 GB · 128K 41.7 GB

IQ2_S

GPT OSS 120B

not listed

GLM 4.5 Air

35.0 GB42.5 GB file

32K 36.9 GB · 128K 43.1 GB

IQ2_M

GPT OSS 120B

39.8 GB~39.4 GB file

32K 40.6 GB · 128K 43.1 GB

GLM 4.5 Air

37.7 GB44.4 GB file

32K 39.6 GB · 128K 45.8 GB

IQ3_XXS

GPT OSS 120B

not listed

GLM 4.5 Air

43.2 GB51.4 GB file

32K 45.2 GB · 128K 51.3 GB

IQ3_XS

GPT OSS 120B

not listed

GLM 4.5 Air

46.0 GB50.8 GB file

32K 47.9 GB · 128K 54.1 GB

IQ3_M

GPT OSS 120B

53.0 GB62.7 GB file

32K 53.7 GB · 128K 56.3 GB

GLM 4.5 Air

50.1 GB55.5 GB file

32K 52.1 GB · 128K 58.2 GB

Q3_K_L

GPT OSS 120B

60.3 GB62.6 GB file

32K 61.0 GB · 128K 63.6 GB

GLM 4.5 Air

57.0 GB55.9 GB file

32K 59.0 GB · 128K 65.1 GB

IQ4_XS

GPT OSS 120B

63.2 GB62.7 GB file

32K 64.0 GB · 128K 66.5 GB

GLM 4.5 Air

59.8 GB60.5 GB file

32K 61.7 GB · 128K 67.9 GB

IQ4_NL

GPT OSS 120B

66.1 GB62.7 GB file

32K 66.9 GB · 128K 69.4 GB

GLM 4.5 Air

62.6 GB62.7 GB file

32K 64.5 GB · 128K 70.7 GB

Q4_1

GPT OSS 120B

66.1 GB62.7 GB file

32K 66.9 GB · 128K 69.4 GB

GLM 4.5 Air

62.6 GB69.4 GB file

32K 64.5 GB · 128K 70.7 GB

Q4_K_S

GPT OSS 120B

66.1 GB62.8 GB file

32K 66.9 GB · 128K 69.4 GB

GLM 4.5 Air

62.6 GB67.0 GB file

32K 64.5 GB · 128K 70.7 GB

Q4_K_L

GPT OSS 120B

72.0 GB63.1 GB file

32K 72.7 GB · 128K 75.3 GB

GLM 4.5 Air

not listed

Q5_K_S

GPT OSS 120B

80.7 GB62.9 GB file

32K 81.5 GB · 128K 84.0 GB

GLM 4.5 Air

76.4 GB78.4 GB file

32K 78.3 GB · 128K 84.5 GB

BF16

GPT OSS 120B

234 GB~233.7 GB file

32K 235 GB · 128K 237 GB

GLM 4.5 Air

221 GB221.0 GB file

32K 223 GB · 128K 229 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 →

GLM 4.5 Air

Ollama · Q4_K_M

$ollama run hf.co/unsloth/GLM-4.5-Air-GGUF:Q4_K_M

All ways to run GLM 4.5 Air →

Specifications

Specifications of GPT OSS 120B and GLM 4.5 Air
Spec	GPT OSS 120B	GLM 4.5 Air
Publisher	OpenAI	Z.ai
Parameters	116.8B	110.5B
Active parameters	5.8B per token	15B per token
Architecture	GptOssForCausalLM	Glm4MoeForCausalLM
Context	128K tokens	128K tokens
Modalities	Chat, Function-calling	Chat, Function-calling
License	Apache 2.0	MIT
Released	Aug 2025	Jul 2025

Frequently Asked Questions

Which is better, GPT OSS 120B or GLM 4.5 Air?

GPT OSS 120B and GLM 4.5 Air match in llmrun Score, with values of 97.6 versus 96.3; neither fits 24 GB. Choose GLM 4.5 Air for fits a 48 GB GPU.

Which needs less VRAM, GPT OSS 120B or GLM 4.5 Air?

At Q4_K_M, GPT OSS 120B requires 70.5 GB while GLM 4.5 Air needs 66.7 GB, making GLM 4.5 Air the easier model to run on your local setup.

Can I run GPT OSS 120B or GLM 4.5 Air on a 16 GB GPU?

GPT OSS 120B does not fit (smallest quant needs 40.2 GB); GLM 4.5 Air does not fit (smallest quant needs 31.7 GB).

Which has a longer context window, GPT OSS 120B or GLM 4.5 Air?

GPT OSS 120B supports 131,072 tokens and GLM 4.5 Air supports 131,072 tokens.