Mistral Medium 3.5 128B vs Qwen2.5 72B Instruct

Mistral Medium 3.5 128B leads llmrun Score 102.1 to 82.2; neither fits 24 GB.

Run Mistral Medium 3.5 128B in the cloud →

Model A · Mistral AI

Mistral Medium 3.5 128B

102.1llmrun Score

127.7B · 256K context · Other · Mar 2026

ChatFunctions

Model B · Alibaba

Qwen2.5 72B Instruct

82.2llmrun Score

72.7B · 32K context · Other · Sep 2024

ChatFunctions

Which should you choose?

Choose Mistral Medium 3.5 128B if you want…

Higher llmrun Score
102.1 vs 82.2
Stronger at reasoning
101.5 vs 88.0
Ahead on the benchmarks
3 of 3 shared boards
Longer context window
256K vs 32K tokens
Newer release
Mar 2026 vs Sep 2024

Choose Qwen2.5 72B Instruct if you want…

Fits a 48 GB GPU
Q4_K_M · 49.3 GB; Mistral Medium 3.5 128B needs 41.3 GB at its smallest quant
Lighter on memory
44.6 vs 77.7 GB at Q4_K_M

On your hardware

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

MemoryMistral Medium 3.5 128BQwen2.5 72B Instruct

8 GB

RTX 4060 · 8 GB tier

Mistral Medium 3.5 128B

Doesn't fit

smallest quant needs 41.3 GB

Qwen2.5 72B Instruct

Doesn't fit

smallest quant needs 25.7 GB

12 GB

RTX 3060 12GB · 12 GB tier

Mistral Medium 3.5 128B

Doesn't fit

smallest quant needs 41.3 GB

Qwen2.5 72B Instruct

Doesn't fit

smallest quant needs 25.7 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Mistral Medium 3.5 128B

Doesn't fit

smallest quant needs 41.3 GB

Qwen2.5 72B Instruct

Doesn't fit

smallest quant needs 25.7 GB

24 GBreference

RTX 4090 · 24 GB tier

Mistral Medium 3.5 128B

Doesn't fit

smallest quant needs 41.3 GB

Qwen2.5 72B Instruct

Doesn't fit

smallest quant needs 25.7 GB

32 GB

RTX 5090 · 32 GB tier

Mistral Medium 3.5 128B

Doesn't fit

smallest quant needs 41.3 GB

Qwen2.5 72B Instruct

IQ2_M · ~46 tok/s

30.2 GB · up to 16Kfits

48 GB

RTX A6000 · 48 GB tier

Mistral Medium 3.5 128B

IQ2_S · ~12 tok/s

46.1 GB · up to 16Kmore headroom

Qwen2.5 72B Instruct

Q4_K_M · ~11 tok/stight

49.3 GB · up to 8K

Mac 32 GB

Mac Mini M4 · Macs

Mistral Medium 3.5 128B

Doesn't fit

smallest quant needs 41.3 GB

Qwen2.5 72B Instruct

IQ2_S · ~4 tok/s

28.4 GB · up to 16Kfits

Mac 64 GB

Mac Studio M4 Max · Macs

Mistral Medium 3.5 128B

IQ3_S · ~7 tok/s

60.5 GB · up to 16K

Qwen2.5 72B Instruct

Q4_K_M · ~9 tok/s

49.3 GB · up to 32Kmore headroom

Mac 128 GB

Mac Studio M4 Max · Macs

Mistral Medium 3.5 128B

Q4_K_M · ~5 tok/s

82.8 GB · up to 128K

Qwen2.5 72B Instruct

Q4_K_M · ~9 tok/s

49.3 GB · up to 32Kfaster

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

Mistral Medium 3.5 128B Qwen2.5 72B Instruct

Overall

Mistral Medium 3.5 128B

102.197–107

Qwen2.5 72B Instruct

82.278–87

Coding

Mistral Medium 3.5 128B

102.296–108

Qwen2.5 72B Instruct

no data

Science

Mistral Medium 3.5 128B

101.380–123

Qwen2.5 72B Instruct

no data

Reasoning

Mistral Medium 3.5 128B

101.593–110

Qwen2.5 72B Instruct

88.079–97

Mistral Medium 3.5 128B · #53 of 106 open models · #20 of 62 that fit ≤96 GB

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

Benchmarks

3 shared boards: Mistral Medium 3.5 128B leads 3, Qwen2.5 72B Instruct leads 0 · Benchmarks imported Nov 2026

BoardMistral Medium 3.5 128BQwen2.5 72B Instruct

WeirdML

Mistral Medium 3.5 128B

43.7%#16/47 open

IndependentEpoch AI · Apr 2026

Qwen2.5 72B Instruct

16.0%#42/47 open

IndependentEpoch AI · Sep 2024

DTBench

Mistral Medium 3.5 128B

75.5%#30/70 open

Lab-reportedEpoch AI · Apr 2026

Qwen2.5 72B Instruct

62.9%#42/70 open

Lab-reportedEpoch AI · Sep 2024

LMCA

Mistral Medium 3.5 128B

26.1%#28/56 open

Lab-reportedEpoch AI · Apr 2026

Qwen2.5 72B Instruct

13.4%#46/56 open

Lab-reportedEpoch AI · Sep 2024

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

LMArena Text

Mistral Medium 3.5 128B

1426.4#28/188 open

ArenaLMArena · Oct 2026

Qwen2.5 72B Instruct

1302.9#107/188 open

ArenaLMArena · Oct 2026

Only Mistral Medium 3.5 128B (7)

Only Qwen2.5 72B Instruct (8)

VRAM by quantization

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

QuantMistral Medium 3.5 128BQwen2.5 72B Instruct

Q2_K

Mistral Medium 3.5 128B

55.3 GB46.6 GB file

32K 66.4 GB · 128K 102 GB

Qwen2.5 72B Instruct

31.9 GB29.8 GB file

32K 41.9 GB · 128K —

Q3_K_S

Mistral Medium 3.5 128B

56.9 GB54.4 GB file

32K 68.0 GB · 128K 103 GB

Qwen2.5 72B Instruct

32.8 GB34.5 GB file

32K 42.9 GB · 128K —

Q3_K_M

Mistral Medium 3.5 128B

63.3 GB60.6 GB file

32K 74.4 GB · 128K 110 GB

Qwen2.5 72B Instruct

36.4 GB37.7 GB file

32K 46.5 GB · 128K —

Q4_0

Mistral Medium 3.5 128B

64.9 GB71.0 GB file

32K 76.0 GB · 128K 111 GB

Qwen2.5 72B Instruct

37.3 GB41.4 GB file

32K 47.4 GB · 128K —

Q4_K_M

Mistral Medium 3.5 128B

77.7 GB74.9 GB file

32K 88.7 GB · 128K 124 GB

Qwen2.5 72B Instruct

44.6 GB47.4 GB file

32K 54.7 GB · 128K —

Q5_K_M

Mistral Medium 3.5 128B

92.0 GB88.3 GB file

32K 103 GB · 128K 139 GB

Qwen2.5 72B Instruct

52.8 GB54.4 GB file

32K 62.8 GB · 128K —

Q6_K

Mistral Medium 3.5 128B

106 GB102.6 GB file

32K 117 GB · 128K 153 GB

Qwen2.5 72B Instruct

61.0 GB64.3 GB file

32K 71.0 GB · 128K —

Q8_0

Mistral Medium 3.5 128B

129 GB132.9 GB file

32K 140 GB · 128K 175 GB

Qwen2.5 72B Instruct

73.7 GB77.3 GB file

32K 83.8 GB · 128K —

19 more quants

IQ2_XXS

Mistral Medium 3.5 128B

36.2 GB34.9 GB file

32K 47.2 GB · 128K 82.7 GB

Qwen2.5 72B Instruct

21.0 GB25.5 GB file

32K 31.0 GB · 128K —

IQ2_XS

Mistral Medium 3.5 128B

39.4 GB43.4 GB file

32K 50.4 GB · 128K 85.9 GB

Qwen2.5 72B Instruct

22.8 GB27.1 GB file

32K 32.9 GB · 128K —

IQ2_S

Mistral Medium 3.5 128B

41.0 GB46.1 GB file

32K 52.0 GB · 128K 87.5 GB

Qwen2.5 72B Instruct

23.7 GB27.9 GB file

32K 33.8 GB · 128K —

IQ2_M

Mistral Medium 3.5 128B

44.1 GB44.1 GB file

32K 55.2 GB · 128K 90.7 GB

Qwen2.5 72B Instruct

25.5 GB29.3 GB file

32K 35.6 GB · 128K —

IQ3_XXS

Mistral Medium 3.5 128B

50.5 GB49.3 GB file

32K 61.6 GB · 128K 97.0 GB

Qwen2.5 72B Instruct

29.1 GB31.8 GB file

32K 39.2 GB · 128K —

Q2_K_S

Mistral Medium 3.5 128B

52.1 GB43.0 GB file

32K 63.2 GB · 128K 98.6 GB

Qwen2.5 72B Instruct

30.1 GB29.6 GB file

32K 40.1 GB · 128K —

IQ3_XS

Mistral Medium 3.5 128B

53.7 GB54.9 GB file

32K 64.8 GB · 128K 100 GB

Qwen2.5 72B Instruct

31.0 GB32.8 GB file

32K 41.0 GB · 128K —

IQ3_S

Mistral Medium 3.5 128B

55.3 GB54.5 GB file

32K 66.4 GB · 128K 102 GB

Qwen2.5 72B Instruct

31.9 GB34.5 GB file

32K 41.9 GB · 128K —

IQ3_M

Mistral Medium 3.5 128B

58.5 GB59.5 GB file

32K 69.6 GB · 128K 105 GB

Qwen2.5 72B Instruct

33.7 GB35.5 GB file

32K 43.8 GB · 128K —

Q3_K_L

Mistral Medium 3.5 128B

66.5 GB67.0 GB file

32K 77.6 GB · 128K 113 GB

Qwen2.5 72B Instruct

38.2 GB39.5 GB file

32K 48.3 GB · 128K —

IQ4_XS

Mistral Medium 3.5 128B

69.7 GB67.1 GB file

32K 80.8 GB · 128K 116 GB

Qwen2.5 72B Instruct

40.1 GB39.7 GB file

32K 50.1 GB · 128K —

IQ4_NL

Mistral Medium 3.5 128B

72.9 GB70.9 GB file

32K 83.9 GB · 128K 119 GB

Qwen2.5 72B Instruct

41.9 GB41.3 GB file

32K 51.9 GB · 128K —

Q4_1

Mistral Medium 3.5 128B

72.9 GB78.5 GB file

32K 83.9 GB · 128K 119 GB

Qwen2.5 72B Instruct

41.9 GB45.7 GB file

32K 51.9 GB · 128K —

Q4_K_S

Mistral Medium 3.5 128B

72.9 GB71.2 GB file

32K 83.9 GB · 128K 119 GB

Qwen2.5 72B Instruct

41.9 GB43.9 GB file

32K 51.9 GB · 128K —

Q4_K_L

Mistral Medium 3.5 128B

79.3 GB79.6 GB file

32K 90.3 GB · 128K 126 GB

Qwen2.5 72B Instruct

not listed

Q5_0

Mistral Medium 3.5 128B

not listed

Qwen2.5 72B Instruct

46.4 GB50.3 GB file

32K 56.5 GB · 128K —

Q5_K_S

Mistral Medium 3.5 128B

88.8 GB86.2 GB file

32K 99.9 GB · 128K 135 GB

Qwen2.5 72B Instruct

51.0 GB51.4 GB file

32K 61.0 GB · 128K —

Q5_K_L

Mistral Medium 3.5 128B

93.6 GB92.1 GB file

32K 105 GB · 128K 140 GB

Qwen2.5 72B Instruct

not listed

BF16

Mistral Medium 3.5 128B

256 GB250.1 GB file

32K 268 GB · 128K 303 GB

Qwen2.5 72B Instruct

146 GB~145.4 GB file

32K 156 GB · 128K —

How to run each

Mistral Medium 3.5 128B

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Mistral-Medium-3.5-128B-GGUF:Q4_K_M

All ways to run Mistral Medium 3.5 128B →

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 →

Specifications

Specifications of Mistral Medium 3.5 128B and Qwen2.5 72B Instruct
Spec	Mistral Medium 3.5 128B	Qwen2.5 72B Instruct
Publisher	Mistral AI	Alibaba
Parameters	127.7B	72.7B
Architecture	Mistral3ForConditionalGeneration	Qwen2ForCausalLM
Context	256K tokens	32K tokens
Modalities	Chat, Function-calling	Chat, Function-calling
License	Other	Other
Released	Mar 2026	Sep 2024

Frequently Asked Questions

Which is better, Mistral Medium 3.5 128B or Qwen2.5 72B Instruct?

Mistral Medium 3.5 128B leads llmrun Score 102.1 to 82.2; neither fits 24 GB. Choose Mistral Medium 3.5 128B for higher llmrun Score and stronger at reasoning; choose Qwen2.5 72B Instruct for fits a 48 GB GPU and lighter on memory.

Which needs less VRAM, Mistral Medium 3.5 128B or Qwen2.5 72B Instruct?

At Q4_K_M, Mistral Medium 3.5 128B requires 77.7 GB while Qwen2.5 72B Instruct needs 44.6 GB, making Qwen2.5 72B Instruct the easier model to run on your local setup.

Can I run Mistral Medium 3.5 128B or Qwen2.5 72B Instruct on a 16 GB GPU?

Mistral Medium 3.5 128B does not fit (smallest quant needs 41.3 GB); Qwen2.5 72B Instruct does not fit (smallest quant needs 25.7 GB).

Which has a longer context window, Mistral Medium 3.5 128B or Qwen2.5 72B Instruct?

Mistral Medium 3.5 128B supports 262,144 tokens and Qwen2.5 72B Instruct supports 32,768 tokens.