Qwen2.5 72B Instruct vs Qwen2 72B Instruct

Qwen2.5 72B Instruct leads llmrun Score 82.2 to 77.5 (ranges overlap); neither fits 24 GB.

Run Qwen2.5 72B Instruct in the cloud →

Model A · Alibaba

Qwen2.5 72B Instruct

82.2llmrun Score

72.7B · 32K context · Other · Sep 2024

ChatFunctions

Model B · Alibaba

Qwen2 72B Instruct

77.5llmrun Score

72.7B · 32K context · Other · May 2024

Chat

Which should you choose?

Choose Qwen2.5 72B Instruct if you want…

Higher llmrun Score
82.2 vs 77.5, ranges overlap
Ahead on the benchmarks
4 of 4 shared boards
Also does function-calling
Qwen2 72B Instruct doesn't list it
Newer release
Sep 2024 vs May 2024

Qwen2 72B Instruct: no clear edge over Qwen2.5 72B Instruct 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%.

MemoryQwen2.5 72B InstructQwen2 72B Instruct

8 GB

RTX 4060 · 8 GB tier

Qwen2.5 72B Instruct

Doesn't fit

smallest quant needs 25.7 GB

Qwen2 72B Instruct

Doesn't fit

smallest quant needs 25.7 GB

12 GB

RTX 3060 12GB · 12 GB tier

Qwen2.5 72B Instruct

Doesn't fit

smallest quant needs 25.7 GB

Qwen2 72B Instruct

Doesn't fit

smallest quant needs 25.7 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Qwen2.5 72B Instruct

Doesn't fit

smallest quant needs 25.7 GB

Qwen2 72B Instruct

Doesn't fit

smallest quant needs 25.7 GB

24 GBreference

RTX 4090 · 24 GB tier

Qwen2.5 72B Instruct

Doesn't fit

smallest quant needs 25.7 GB

Qwen2 72B Instruct

Doesn't fit

smallest quant needs 25.7 GB

32 GB

RTX 5090 · 32 GB tier

Qwen2.5 72B Instruct

IQ2_M · ~46 tok/s

30.2 GB · up to 16K

Qwen2 72B Instruct

IQ2_M · ~46 tok/s

30.2 GB · up to 16K

48 GB

RTX A6000 · 48 GB tier

Qwen2.5 72B Instruct

Q4_K_M · ~11 tok/stight

49.3 GB · up to 8K

Qwen2 72B Instruct

Q4_K_M · ~11 tok/stight

49.3 GB · up to 8K

Mac 32 GB

Mac Mini M4 · Macs

Qwen2.5 72B Instruct

IQ2_S · ~4 tok/s

28.4 GB · up to 16K

Qwen2 72B Instruct

IQ2_S · ~4 tok/s

28.4 GB · up to 16K

Mac 64 GB

Mac Studio M4 Max · Macs

Qwen2.5 72B Instruct

Q4_K_M · ~9 tok/s

49.3 GB · up to 32K

Qwen2 72B Instruct

Q4_K_M · ~9 tok/s

49.3 GB · up to 32K

Mac 128 GB

Mac Studio M4 Max · Macs

Qwen2.5 72B Instruct

Q4_K_M · ~9 tok/s

49.3 GB · up to 32K

Qwen2 72B Instruct

Q4_K_M · ~9 tok/s

49.3 GB · up to 32K

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

Qwen2.5 72B Instruct Qwen2 72B Instruct

Overall

Qwen2.5 72B Instruct

82.278–87

Qwen2 72B Instruct

77.571–84

Reasoning

Qwen2.5 72B Instruct

88.079–97

Qwen2 72B Instruct

no data

Qwen2.5 72B Instruct · #84 of 106 open models · #30 of 51 that fit ≤64 GB

Qwen2 72B Instruct · #94 of 106 open models · #40 of 51 that fit ≤64 GB

Benchmarks

4 shared boards: Qwen2.5 72B Instruct leads 4, Qwen2 72B Instruct leads 0 · Benchmarks imported Nov 2026

BoardQwen2.5 72B InstructQwen2 72B Instruct

GPQA Diamond

Qwen2.5 72B Instruct

49.1%#56/100 open

IndependentEpoch AI · Sep 2024

Qwen2 72B Instruct

40.8%#71/100 open

IndependentEpoch AI · Jun 2024

MMLU-Pro

Qwen2.5 72B Instruct

71.6%#35/146 open

IndependentTIGER-Lab

Qwen2 72B Instruct

64.4%#49/146 open

IndependentTIGER-Lab

MATH Level 5

Qwen2.5 72B Instruct

63.2%#11/39 open

IndependentEpoch AI · Sep 2024

Qwen2 72B Instruct

39.1%#22/39 open

IndependentEpoch AI · Jun 2024

WeirdML

Qwen2.5 72B Instruct

16.0%#42/47 open

IndependentEpoch AI · Sep 2024

Qwen2 72B Instruct

11.3%#44/47 open

IndependentEpoch AI · Jun 2024

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

LMArena Text

Qwen2.5 72B Instruct

1302.9#107/188 open

ArenaLMArena · Oct 2026

Qwen2 72B Instruct

1261.9#127/188 open

ArenaLMArena · Oct 2026

MMLU

Qwen2.5 72B Instruct

85.3%#3/85 open

Lab-reportedEpoch AI · Sep 2024

Qwen2 72B Instruct

82.4%#8/85 open

Lab-reportedEpoch AI · Jun 2024

METR Time Horizons

Qwen2.5 72B Instruct

35.8%#7/9 open

Lab-reportedEpoch AI · Sep 2024

Qwen2 72B Instruct

29.9%#8/9 open

Lab-reportedEpoch AI · Jun 2024

Only Qwen2.5 72B Instruct (5)

VRAM by quantization

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

QuantQwen2.5 72B InstructQwen2 72B Instruct

Q2_K

Qwen2.5 72B Instruct

31.9 GB29.8 GB file

32K 41.9 GB · 128K —

Qwen2 72B Instruct

31.9 GB29.8 GB file

32K 41.9 GB · 128K —

Q3_K_S

Qwen2.5 72B Instruct

32.8 GB34.5 GB file

32K 42.9 GB · 128K —

Qwen2 72B Instruct

32.8 GB34.5 GB file

32K 42.9 GB · 128K —

Q3_K_M

Qwen2.5 72B Instruct

36.4 GB37.7 GB file

32K 46.5 GB · 128K —

Qwen2 72B Instruct

36.4 GB37.7 GB file

32K 46.5 GB · 128K —

Q4_0

Qwen2.5 72B Instruct

37.3 GB41.4 GB file

32K 47.4 GB · 128K —

Qwen2 72B Instruct

37.3 GB41.2 GB file

32K 47.4 GB · 128K —

Q4_K_M

Qwen2.5 72B Instruct

44.6 GB47.4 GB file

32K 54.7 GB · 128K —

Qwen2 72B Instruct

44.6 GB47.4 GB file

32K 54.7 GB · 128K —

Q5_K_M

Qwen2.5 72B Instruct

52.8 GB54.4 GB file

32K 62.8 GB · 128K —

Qwen2 72B Instruct

52.8 GB54.4 GB file

32K 62.8 GB · 128K —

Q6_K

Qwen2.5 72B Instruct

61.0 GB64.3 GB file

32K 71.0 GB · 128K —

Qwen2 72B Instruct

61.0 GB64.3 GB file

32K 71.0 GB · 128K —

Q8_0

Qwen2.5 72B Instruct

73.7 GB77.3 GB file

32K 83.8 GB · 128K —

Qwen2 72B Instruct

73.7 GB77.3 GB file

32K 83.8 GB · 128K —

17 more quants

IQ2_XXS

Qwen2.5 72B Instruct

21.0 GB25.5 GB file

32K 31.0 GB · 128K —

Qwen2 72B Instruct

21.0 GB25.5 GB file

32K 31.0 GB · 128K —

IQ2_XS

Qwen2.5 72B Instruct

22.8 GB27.1 GB file

32K 32.9 GB · 128K —

Qwen2 72B Instruct

22.8 GB27.1 GB file

32K 32.9 GB · 128K —

IQ2_S

Qwen2.5 72B Instruct

23.7 GB27.9 GB file

32K 33.8 GB · 128K —

Qwen2 72B Instruct

23.7 GB27.9 GB file

32K 33.8 GB · 128K —

IQ2_M

Qwen2.5 72B Instruct

25.5 GB29.3 GB file

32K 35.6 GB · 128K —

Qwen2 72B Instruct

25.5 GB29.3 GB file

32K 35.6 GB · 128K —

IQ3_XXS

Qwen2.5 72B Instruct

29.1 GB31.8 GB file

32K 39.2 GB · 128K —

Qwen2 72B Instruct

29.1 GB31.8 GB file

32K 39.2 GB · 128K —

Q2_K_S

Qwen2.5 72B Instruct

30.1 GB29.6 GB file

32K 40.1 GB · 128K —

Qwen2 72B Instruct

not listed

IQ3_XS

Qwen2.5 72B Instruct

31.0 GB32.8 GB file

32K 41.0 GB · 128K —

Qwen2 72B Instruct

31.0 GB32.8 GB file

32K 41.0 GB · 128K —

IQ3_S

Qwen2.5 72B Instruct

31.9 GB34.5 GB file

32K 41.9 GB · 128K —

Qwen2 72B Instruct

31.9 GB34.5 GB file

32K 41.9 GB · 128K —

IQ3_M

Qwen2.5 72B Instruct

33.7 GB35.5 GB file

32K 43.8 GB · 128K —

Qwen2 72B Instruct

33.7 GB35.5 GB file

32K 43.8 GB · 128K —

Q3_K_L

Qwen2.5 72B Instruct

38.2 GB39.5 GB file

32K 48.3 GB · 128K —

Qwen2 72B Instruct

38.2 GB39.5 GB file

32K 48.3 GB · 128K —

IQ4_XS

Qwen2.5 72B Instruct

40.1 GB39.7 GB file

32K 50.1 GB · 128K —

Qwen2 72B Instruct

40.1 GB39.7 GB file

32K 50.1 GB · 128K —

IQ4_NL

Qwen2.5 72B Instruct

41.9 GB41.3 GB file

32K 51.9 GB · 128K —

Qwen2 72B Instruct

not listed

Q4_1

Qwen2.5 72B Instruct

41.9 GB45.7 GB file

32K 51.9 GB · 128K —

Qwen2 72B Instruct

not listed

Q4_K_S

Qwen2.5 72B Instruct

41.9 GB43.9 GB file

32K 51.9 GB · 128K —

Qwen2 72B Instruct

41.9 GB43.9 GB file

32K 51.9 GB · 128K —

Q5_0

Qwen2.5 72B Instruct

46.4 GB50.3 GB file

32K 56.5 GB · 128K —

Qwen2 72B Instruct

46.4 GB50.2 GB file

32K 56.5 GB · 128K —

Q5_K_S

Qwen2.5 72B Instruct

51.0 GB51.4 GB file

32K 61.0 GB · 128K —

Qwen2 72B Instruct

51.0 GB51.4 GB file

32K 61.0 GB · 128K —

BF16

Qwen2.5 72B Instruct

146 GB~145.4 GB file

32K 156 GB · 128K —

Qwen2 72B Instruct

146 GB~145.4 GB file

32K 156 GB · 128K —

How to run each

Qwen2.5 72B Instruct

Ollama · Q4_K_M

$ollama run hf.co/bartowski/Qwen2.5-72B-Instruct-GGUF:Q4_K_M

All ways to run Qwen2.5 72B Instruct →

Qwen2 72B Instruct

Ollama · Q4_K_M

$ollama run hf.co/second-state/Qwen2-72B-Instruct-GGUF:Q4_K_M

All ways to run Qwen2 72B Instruct →

Specifications

Specifications of Qwen2.5 72B Instruct and Qwen2 72B Instruct
Spec	Qwen2.5 72B Instruct	Qwen2 72B Instruct
Publisher	Alibaba	Alibaba
Parameters	72.7B	72.7B
Architecture	Qwen2ForCausalLM	Qwen2ForCausalLM
Context	32K tokens	32K tokens
Modalities	Chat, Function-calling	Chat
License	Other	Other
Released	Sep 2024	May 2024

Frequently Asked Questions

Which is better, Qwen2.5 72B Instruct or Qwen2 72B Instruct?

Qwen2.5 72B Instruct leads llmrun Score 82.2 to 77.5 (ranges overlap); neither fits 24 GB. Choose Qwen2.5 72B Instruct for higher llmrun Score and ahead on the benchmarks.

Which needs less VRAM, Qwen2.5 72B Instruct or Qwen2 72B Instruct?

At Q4_K_M, Qwen2.5 72B Instruct requires 44.6 GB while Qwen2 72B Instruct needs 44.6 GB, making Qwen2.5 72B Instruct the easier model to run on your local setup.

Can I run Qwen2.5 72B Instruct or Qwen2 72B Instruct on a 16 GB GPU?

Qwen2.5 72B Instruct does not fit (smallest quant needs 25.7 GB); Qwen2 72B Instruct does not fit (smallest quant needs 25.7 GB).

Which has a longer context window, Qwen2.5 72B Instruct or Qwen2 72B Instruct?

Qwen2.5 72B Instruct supports 32,768 tokens and Qwen2 72B Instruct supports 32,768 tokens.