Qwen3.8 27B vs GLM 4.5 Air

Qwen3.8 27B leads llmrun Score 121.5 to 96.3; only Qwen3.8 27B fits 24 GB (Q4_K_M); GLM 4.5 Air needs 31.7 GB even at its smallest quant.

Model A · Alibaba

Qwen3.8 27B

121.5llmrun Score

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

VisionFunctions

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 Qwen3.8 27B if you want…

Higher llmrun Score
121.5 vs 96.3
Fits a 12 GB GPU
IQ3_XXS · 12 GB; GLM 4.5 Air needs 31.7 GB at its smallest quant
Fits a Mac 32 GB
Q4_K_M · 17.9 GB; GLM 4.5 Air needs 31.7 GB at its smallest quant
Lighter on memory
17.4 vs 66.7 GB at Q4_K_M
Longer context window
256K vs 128K tokens
Also does vision
GLM 4.5 Air doesn't list it

Choose GLM 4.5 Air if you want…

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

On your hardware

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

MemoryQwen3.8 27BGLM 4.5 Air

8 GB

RTX 4060 · 8 GB tier

Qwen3.8 27B

Doesn't fit

smallest quant needs 8.8 GB

GLM 4.5 Air

Doesn't fit

smallest quant needs 31.7 GB

12 GB

RTX 3060 12GB · 12 GB tier

Qwen3.8 27B

IQ3_XXS · ~20 tok/s

12 GB · up to 16Kfits

GLM 4.5 Air

Doesn't fit

smallest quant needs 31.7 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Qwen3.8 27B

Q3_K_L · ~19 tok/s

15.4 GB · up to 16Kfits

GLM 4.5 Air

Doesn't fit

smallest quant needs 31.7 GB

24 GBreference

RTX 4090 · 24 GB tier

Qwen3.8 27B

Q4_K_M · ~38 tok/s

17.9 GB · up to 64Kfits

GLM 4.5 Air

Doesn't fit

smallest quant needs 31.7 GB

32 GB

RTX 5090 · 32 GB tier

Qwen3.8 27B

Q4_K_M · ~67 tok/s

17.9 GB · up to 256Kmore headroom

GLM 4.5 Air

IQ2_XXS · ~164 tok/s

31.7 GB · up to 16K

48 GB

RTX A6000 · 48 GB tier

Qwen3.8 27B

Q4_K_M · ~29 tok/s

17.9 GB · up to 256Kmore headroom

GLM 4.5 Air

IQ3_XS · ~67 tok/s

46.9 GB · up to 32K

Mac 32 GB

Mac Mini M4 · Macs

Qwen3.8 27B

Q4_K_M · ~5 tok/s

17.9 GB · up to 128Kfits

GLM 4.5 Air

Doesn't fit

smallest quant needs 31.7 GB

Mac 64 GB

Mac Studio M4 Max · Macs

Qwen3.8 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256Kmore headroom

GLM 4.5 Air

Q3_K_L · ~34 tok/s

57.9 GB · up to 32K

Mac 128 GB

Mac Studio M4 Max · Macs

Qwen3.8 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256K

GLM 4.5 Air

Q4_K_M · ~30 tok/s

67.6 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

Qwen3.8 27B GLM 4.5 Air

Overall

Qwen3.8 27B

121.5119–124

GLM 4.5 Air

96.386–107

Coding

Qwen3.8 27B

112.1105–119

GLM 4.5 Air

no data

Math

Qwen3.8 27B

117.5111–125

GLM 4.5 Air

no data

Science

Qwen3.8 27B

112.093–131

GLM 4.5 Air

no data

Reasoning

Qwen3.8 27B

124.1121–127

GLM 4.5 Air

no data

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

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

Benchmarks

1 shared board: Qwen3.8 27B leads 1, GLM 4.5 Air leads 0 · Benchmarks imported Oct 2026

BoardQwen3.8 27BGLM 4.5 Air

LMArena Text

Qwen3.8 27B

1438.1#22/186 open

ArenaLMArena · Oct 2026

GLM 4.5 Air

1373.1#62/186 open

ArenaLMArena · Oct 2026

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

Only Qwen3.8 27B (13)

Only GLM 4.5 Air (4)

VRAM by quantization

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

QuantQwen3.8 27BGLM 4.5 Air

Q2_K

Qwen3.8 27B

12.6 GB10.8 GB file

32K 13.9 GB · 128K 19.3 GB

GLM 4.5 Air

47.4 GB45.3 GB file

32K 49.3 GB · 128K 55.5 GB

Q3_K_S

Qwen3.8 27B

12.9 GB12.7 GB file

32K 14.2 GB · 128K 19.6 GB

GLM 4.5 Air

48.8 GB52.7 GB file

32K 50.7 GB · 128K 56.9 GB

Q3_K_M

Qwen3.8 27B

14.3 GB13.4 GB file

32K 15.6 GB · 128K 21.0 GB

GLM 4.5 Air

54.3 GB57.2 GB file

32K 56.2 GB · 128K 62.4 GB

Q4_0

Qwen3.8 27B

14.6 GB~13.9 GB file

32K 16.0 GB · 128K 21.4 GB

GLM 4.5 Air

55.7 GB62.8 GB file

32K 57.6 GB · 128K 63.8 GB

Q4_K_M

Qwen3.8 27B

17.4 GB16.5 GB file

32K 18.8 GB · 128K 24.1 GB

GLM 4.5 Air

66.7 GB73.0 GB file

32K 68.6 GB · 128K 74.8 GB

Q5_K_M

Qwen3.8 27B

20.5 GB19.8 GB file

32K 21.9 GB · 128K 27.3 GB

GLM 4.5 Air

79.1 GB83.5 GB file

32K 81.1 GB · 128K 87.2 GB

Q6_K

Qwen3.8 27B

23.7 GB22.0 GB file

32K 25.0 GB · 128K 30.4 GB

GLM 4.5 Air

91.6 GB99.0 GB file

32K 93.5 GB · 128K 99.7 GB

Q8_0

Qwen3.8 27B

28.5 GB29.0 GB file

32K 29.9 GB · 128K 35.2 GB

GLM 4.5 Air

111 GB117.5 GB file

32K 113 GB · 128K 119 GB

17 more quants

IQ2_XXS

Qwen3.8 27B

8.4 GB7.3 GB file

32K 9.7 GB · 128K 15.1 GB

GLM 4.5 Air

30.8 GB42.7 GB file

32K 32.7 GB · 128K 38.9 GB

IQ2_XS

Qwen3.8 27B

9.1 GB9.1 GB file

32K 10.4 GB · 128K 15.8 GB

GLM 4.5 Air

33.6 GB42.2 GB file

32K 35.5 GB · 128K 41.7 GB

IQ2_S

Qwen3.8 27B

9.4 GB8.4 GB file

32K 10.8 GB · 128K 16.1 GB

GLM 4.5 Air

35.0 GB42.5 GB file

32K 36.9 GB · 128K 43.1 GB

IQ2_M

Qwen3.8 27B

10.1 GB10.5 GB file

32K 11.5 GB · 128K 16.8 GB

GLM 4.5 Air

37.7 GB44.4 GB file

32K 39.6 GB · 128K 45.8 GB

IQ3_XXS

Qwen3.8 27B

11.5 GB10.9 GB file

32K 12.9 GB · 128K 18.2 GB

GLM 4.5 Air

43.2 GB51.4 GB file

32K 45.2 GB · 128K 51.3 GB

IQ3_XS

Qwen3.8 27B

12.2 GB10.4 GB file

32K 13.6 GB · 128K 18.9 GB

GLM 4.5 Air

46.0 GB50.8 GB file

32K 47.9 GB · 128K 54.1 GB

IQ3_S

Qwen3.8 27B

12.6 GB12.0 GB file

32K 13.9 GB · 128K 19.3 GB

GLM 4.5 Air

not listed

IQ3_M

Qwen3.8 27B

13.3 GB14.9 GB file

32K 14.6 GB · 128K 20.0 GB

GLM 4.5 Air

50.1 GB55.5 GB file

32K 52.1 GB · 128K 58.2 GB

Q3_K_L

Qwen3.8 27B

15.0 GB14.1 GB file

32K 16.3 GB · 128K 21.7 GB

GLM 4.5 Air

57.0 GB55.9 GB file

32K 59.0 GB · 128K 65.1 GB

IQ4_XS

Qwen3.8 27B

15.7 GB14.3 GB file

32K 17.0 GB · 128K 22.4 GB

GLM 4.5 Air

59.8 GB60.5 GB file

32K 61.7 GB · 128K 67.9 GB

IQ4_NL

Qwen3.8 27B

16.4 GB17.4 GB file

32K 17.7 GB · 128K 23.1 GB

GLM 4.5 Air

62.6 GB62.7 GB file

32K 64.5 GB · 128K 70.7 GB

Q4_1

Qwen3.8 27B

16.4 GB17.5 GB file

32K 17.7 GB · 128K 23.1 GB

GLM 4.5 Air

62.6 GB69.4 GB file

32K 64.5 GB · 128K 70.7 GB

Q4_K_S

Qwen3.8 27B

16.4 GB15.4 GB file

32K 17.7 GB · 128K 23.1 GB

GLM 4.5 Air

62.6 GB67.0 GB file

32K 64.5 GB · 128K 70.7 GB

Q4_K_L

Qwen3.8 27B

17.8 GB18.8 GB file

32K 19.1 GB · 128K 24.5 GB

GLM 4.5 Air

not listed

Q5_K_S

Qwen3.8 27B

19.9 GB18.7 GB file

32K 21.2 GB · 128K 26.6 GB

GLM 4.5 Air

76.4 GB78.4 GB file

32K 78.3 GB · 128K 84.5 GB

Q5_K_L

Qwen3.8 27B

20.9 GB21.5 GB file

32K 22.2 GB · 128K 27.6 GB

GLM 4.5 Air

not listed

BF16

Qwen3.8 27B

56.3 GB54.7 GB file

32K 57.7 GB · 128K 63.0 GB

GLM 4.5 Air

221 GB221.0 GB file

32K 223 GB · 128K 229 GB

How to run each

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 →

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 Qwen3.8 27B and GLM 4.5 Air
Spec	Qwen3.8 27B	GLM 4.5 Air
Publisher	Alibaba	Z.ai
Parameters	27.8B	110.5B
Active parameters	—	15B per token
Architecture	Qwen3_5ForConditionalGeneration	Glm4MoeForCausalLM
Context	256K tokens	128K tokens
Modalities	Vision, Function-calling	Chat, Function-calling
License	Apache 2.0	MIT
Released	Aug 2026	Jul 2025

Frequently Asked Questions

Which is better, Qwen3.8 27B or GLM 4.5 Air?

Qwen3.8 27B leads llmrun Score 121.5 to 96.3; only Qwen3.8 27B fits 24 GB (Q4_K_M); GLM 4.5 Air needs 31.7 GB even at its smallest quant. Choose Qwen3.8 27B for higher llmrun Score and fits a 12 GB GPU; choose GLM 4.5 Air for also does chat.

Which needs less VRAM, Qwen3.8 27B or GLM 4.5 Air?

At Q4_K_M, Qwen3.8 27B requires 17.4 GB while GLM 4.5 Air needs 66.7 GB, making Qwen3.8 27B the easier model to run on your local setup.

Can I run Qwen3.8 27B or GLM 4.5 Air on a 16 GB GPU?

Qwen3.8 27B fits at Q3_K_L; GLM 4.5 Air does not fit (smallest quant needs 31.7 GB).

Which has a longer context window, Qwen3.8 27B or GLM 4.5 Air?

Qwen3.8 27B supports 262,144 tokens and GLM 4.5 Air supports 131,072 tokens.