Qwen3.8 27B vs MiMo V2.5 Pro

Qwen3.8 27B leads llmrun Score 122.1 to 116.4 (ranges overlap); only Qwen3.8 27B fits 24 GB (Q4_K_M); MiMo V2.5 Pro needs 283.5 GB even at its smallest quant.

Model A · Alibaba

Qwen3.8 27B

122.1llmrun Score

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

VisionFunctions

Model B · Xiaomi

MiMo V2.5 Pro

116.4llmrun Score

1023.2B · 43.9B active · 1M context · MIT · Apr 2026

ChatFunctionsCode

Which should you choose?

Choose Qwen3.8 27B if you want…

Higher llmrun Score
122.1 vs 116.4, ranges overlap
Stronger at reasoning
124.0 vs 110.8
Fits a 12 GB GPU
IQ3_XXS · 12 GB; MiMo V2.5 Pro needs 283.5 GB at its smallest quant
Fits a Mac 32 GB
Q4_K_M · 17.9 GB; MiMo V2.5 Pro needs 283.5 GB at its smallest quant
Lighter on memory
17.4 vs 614.5 GB at Q4_K_M
Also does vision
MiMo V2.5 Pro doesn't list it

Choose MiMo V2.5 Pro if you want…

Longer context window
1M vs 256K tokens
Also does chat, code
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 27BMiMo V2.5 Pro

8 GB

RTX 4060 · 8 GB tier

Qwen3.8 27B

Doesn't fit

smallest quant needs 8.8 GB

MiMo V2.5 Pro

Doesn't fit

smallest quant needs 283.5 GB

12 GB

RTX 3060 12GB · 12 GB tier

Qwen3.8 27B

IQ3_XXS · ~20 tok/s

12 GB · up to 16Kfits

MiMo V2.5 Pro

Doesn't fit

smallest quant needs 283.5 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

MiMo V2.5 Pro

Doesn't fit

smallest quant needs 283.5 GB

24 GBreference

RTX 4090 · 24 GB tier

Qwen3.8 27B

Q4_K_M · ~38 tok/s

17.9 GB · up to 64Kfits

MiMo V2.5 Pro

Doesn't fit

smallest quant needs 283.5 GB

32 GB

RTX 5090 · 32 GB tier

Qwen3.8 27B

Q4_K_M · ~67 tok/s

17.9 GB · up to 256Kfits

MiMo V2.5 Pro

Doesn't fit

smallest quant needs 283.5 GB

48 GB

RTX A6000 · 48 GB tier

Qwen3.8 27B

Q4_K_M · ~29 tok/s

17.9 GB · up to 256Kfits

MiMo V2.5 Pro

Doesn't fit

smallest quant needs 283.5 GB

Mac 32 GB

Mac Mini M4 · Macs

Qwen3.8 27B

Q4_K_M · ~5 tok/s

17.9 GB · up to 128Kfits

MiMo V2.5 Pro

Doesn't fit

smallest quant needs 283.5 GB

Mac 64 GB

Mac Studio M4 Max · Macs

Qwen3.8 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256Kfits

MiMo V2.5 Pro

Doesn't fit

smallest quant needs 283.5 GB

Mac 128 GB

Mac Studio M4 Max · Macs

Qwen3.8 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256Kfits

MiMo V2.5 Pro

Doesn't fit

smallest quant needs 283.5 GB

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 MiMo V2.5 Pro

Overall

Qwen3.8 27B

122.1120–124

MiMo V2.5 Pro

116.4111–122

Coding

Qwen3.8 27B

119.7114–125

MiMo V2.5 Pro

115.6106–126

Agents

Qwen3.8 27B

122.8117–129

MiMo V2.5 Pro

no data

Math

Qwen3.8 27B

117.5111–124

MiMo V2.5 Pro

no data

Science

Qwen3.8 27B

112.093–131

MiMo V2.5 Pro

114.697–133

Reasoning

Qwen3.8 27B

124.0121–127

MiMo V2.5 Pro

110.8102–120

Qwen3.8 27B · #11 of 100 open models · #1 of 35 that fit 24 GB

MiMo V2.5 Pro · #17 of 100 open models · #14 of 96 that fit ≤640 GB

Benchmarks

5 shared boards: Qwen3.8 27B leads 3, MiMo V2.5 Pro leads 2 · Benchmarks imported Oct 2026

BoardQwen3.8 27BMiMo V2.5 Pro

SciCode

Qwen3.8 27B

46.6%#19/66 open

Lab-reportedEpoch AI · Aug 2026

MiMo V2.5 Pro

50.2%#10/66 open

Lab-reportedEpoch AI

CritPt

Qwen3.8 27B

5.4%#15/66 open

Lab-reportedEpoch AI · Aug 2026

MiMo V2.5 Pro

4.0%#18/66 open

Lab-reportedEpoch AI

DTBench

Qwen3.8 27B

88.0%#9/68 open

Lab-reportedEpoch AI · Aug 2026

MiMo V2.5 Pro

84.5%#16/68 open

Lab-reportedEpoch AI

LMCA

Qwen3.8 27B

41.4%#7/54 open

Lab-reportedEpoch AI · Aug 2026

MiMo V2.5 Pro

29.5%#21/54 open

Lab-reportedEpoch AI

ProofBench

Qwen3.8 27B

16.0%#16/26 open

Lab-reportedEpoch AI · Aug 2026

MiMo V2.5 Pro

22.0%#11/26 open

Lab-reportedEpoch AI

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

LMArena Text

Qwen3.8 27B

1437.8#22/187 open

ArenaLMArena · Oct 2026

MiMo V2.5 Pro

1467.3#7/187 open

ArenaLMArena · Oct 2026

LMArena WebDev

Qwen3.8 27B

1593.2#10/52 open

ArenaLMArena · Oct 2026

MiMo V2.5 Pro

1481.3#18/52 open

ArenaLMArena · Oct 2026

Only Qwen3.8 27B (14)

Only MiMo V2.5 Pro (1)

ALE-Bench899.8

VRAM by quantization

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

QuantQwen3.8 27BMiMo V2.5 Pro

Q2_K

Qwen3.8 27B

12.6 GB10.8 GB file

32K 13.9 GB · 128K 19.3 GB

MiMo V2.5 Pro

435 GB~434.9 GB file

32K 439 GB · 128K 449 GB

Q3_K_S

Qwen3.8 27B

12.9 GB12.7 GB file

32K 14.2 GB · 128K 19.6 GB

MiMo V2.5 Pro

not listed

Q3_K_M

Qwen3.8 27B

14.3 GB13.4 GB file

32K 15.6 GB · 128K 21.0 GB

MiMo V2.5 Pro

499 GB459.7 GB file

32K 503 GB · 128K 513 GB

Q4_0

Qwen3.8 27B

14.6 GB~13.9 GB file

32K 16.0 GB · 128K 21.4 GB

MiMo V2.5 Pro

not listed

Q4_K_M

Qwen3.8 27B

17.4 GB16.5 GB file

32K 18.8 GB · 128K 24.1 GB

MiMo V2.5 Pro

614 GB629.6 GB file

32K 618 GB · 128K 628 GB

Q5_K_M

Qwen3.8 27B

20.5 GB19.8 GB file

32K 21.9 GB · 128K 27.3 GB

MiMo V2.5 Pro

730 GB758.0 GB file

32K 733 GB · 128K 743 GB

Q6_K

Qwen3.8 27B

23.7 GB22.0 GB file

32K 25.0 GB · 128K 30.4 GB

MiMo V2.5 Pro

845 GB846.6 GB file

32K 848 GB · 128K 859 GB

Q8_0

Qwen3.8 27B

28.5 GB29.0 GB file

32K 29.9 GB · 128K 35.2 GB

MiMo V2.5 Pro

1024 GB1087.6 GB file

32K 1027 GB · 128K 1038 GB

17 more quants

IQ2_XXS

Qwen3.8 27B

8.4 GB7.3 GB file

32K 9.7 GB · 128K 15.1 GB

MiMo V2.5 Pro

282 GB317.2 GB file

32K 285 GB · 128K 296 GB

IQ2_XS

Qwen3.8 27B

9.1 GB9.1 GB file

32K 10.4 GB · 128K 15.8 GB

MiMo V2.5 Pro

not listed

IQ2_S

Qwen3.8 27B

9.4 GB8.4 GB file

32K 10.8 GB · 128K 16.1 GB

MiMo V2.5 Pro

320 GB319.4 GB file

32K 324 GB · 128K 334 GB

IQ2_M

Qwen3.8 27B

10.1 GB10.5 GB file

32K 11.5 GB · 128K 16.8 GB

MiMo V2.5 Pro

346 GB317.3 GB file

32K 349 GB · 128K 360 GB

IQ3_XXS

Qwen3.8 27B

11.5 GB10.9 GB file

32K 12.9 GB · 128K 18.2 GB

MiMo V2.5 Pro

397 GB412.7 GB file

32K 400 GB · 128K 411 GB

IQ3_XS

Qwen3.8 27B

12.2 GB10.4 GB file

32K 13.6 GB · 128K 18.9 GB

MiMo V2.5 Pro

not listed

IQ3_S

Qwen3.8 27B

12.6 GB12.0 GB file

32K 13.9 GB · 128K 19.3 GB

MiMo V2.5 Pro

435 GB377.9 GB file

32K 439 GB · 128K 449 GB

IQ3_M

Qwen3.8 27B

13.3 GB14.9 GB file

32K 14.6 GB · 128K 20.0 GB

MiMo V2.5 Pro

not listed

Q3_K_L

Qwen3.8 27B

15.0 GB14.1 GB file

32K 16.3 GB · 128K 21.7 GB

MiMo V2.5 Pro

not listed

IQ4_XS

Qwen3.8 27B

15.7 GB14.3 GB file

32K 17.0 GB · 128K 22.4 GB

MiMo V2.5 Pro

551 GB490.7 GB file

32K 554 GB · 128K 564 GB

IQ4_NL

Qwen3.8 27B

16.4 GB17.4 GB file

32K 17.7 GB · 128K 23.1 GB

MiMo V2.5 Pro

576 GB501.3 GB file

32K 579 GB · 128K 590 GB

Q4_1

Qwen3.8 27B

16.4 GB17.5 GB file

32K 17.7 GB · 128K 23.1 GB

MiMo V2.5 Pro

not listed

Q4_K_S

Qwen3.8 27B

16.4 GB15.4 GB file

32K 17.7 GB · 128K 23.1 GB

MiMo V2.5 Pro

576 GB588.5 GB file

32K 579 GB · 128K 590 GB

Q4_K_L

Qwen3.8 27B

17.8 GB18.8 GB file

32K 19.1 GB · 128K 24.5 GB

MiMo V2.5 Pro

not listed

Q5_K_S

Qwen3.8 27B

19.9 GB18.7 GB file

32K 21.2 GB · 128K 26.6 GB

MiMo V2.5 Pro

704 GB713.2 GB file

32K 707 GB · 128K 718 GB

Q5_K_L

Qwen3.8 27B

20.9 GB21.5 GB file

32K 22.2 GB · 128K 27.6 GB

MiMo V2.5 Pro

not listed

BF16

Qwen3.8 27B

56.3 GB54.7 GB file

32K 57.7 GB · 128K 63.0 GB

MiMo V2.5 Pro

2047 GB2046.7 GB file

32K 2050 GB · 128K 2061 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 →

MiMo V2.5 Pro

Ollama · Q4_K_M

$ollama run hf.co/unsloth/MiMo-V2.5-Pro-GGUF:Q4_K_M

All ways to run MiMo V2.5 Pro →

Specifications

Specifications of Qwen3.8 27B and MiMo V2.5 Pro
Spec	Qwen3.8 27B	MiMo V2.5 Pro
Publisher	Alibaba	Xiaomi
Parameters	27.8B	1023.2B
Active parameters	—	44B per token
Architecture	Qwen3_5ForConditionalGeneration	MiMoV2ForCausalLM
Context	256K tokens	1M tokens
Modalities	Vision, Function-calling	Chat, Function-calling, Code
License	Apache 2.0	MIT
Released	Aug 2026	Apr 2026

Frequently Asked Questions

Which is better, Qwen3.8 27B or MiMo V2.5 Pro?

Qwen3.8 27B leads llmrun Score 122.1 to 116.4 (ranges overlap); only Qwen3.8 27B fits 24 GB (Q4_K_M); MiMo V2.5 Pro needs 283.5 GB even at its smallest quant. Choose Qwen3.8 27B for higher llmrun Score and stronger at reasoning; choose MiMo V2.5 Pro for longer context window and also does chat, code.

Which needs less VRAM, Qwen3.8 27B or MiMo V2.5 Pro?

At Q4_K_M, Qwen3.8 27B requires 17.4 GB while MiMo V2.5 Pro needs 614.5 GB, making Qwen3.8 27B the easier model to run on your local setup.

Can I run Qwen3.8 27B or MiMo V2.5 Pro on a 16 GB GPU?

Qwen3.8 27B fits at Q3_K_L; MiMo V2.5 Pro does not fit (smallest quant needs 283.5 GB).

Which has a longer context window, Qwen3.8 27B or MiMo V2.5 Pro?

Qwen3.8 27B supports 262,144 tokens and MiMo V2.5 Pro supports 1,048,576 tokens.