Mistral Small 4 119B 2603 vs Qwen3.8 27B

Qwen3.8 27B leads llmrun Score 122.1 to 96.4; only Qwen3.8 27B fits 24 GB (Q4_K_M); Mistral Small 4 119B 2603 needs 42.8 GB even at its smallest quant.

Model A · Mistral AI

Mistral Small 4 119B 2603

96.4llmrun Score

119.4B · 7.1B active · 1M context · Apache 2.0 · Jan 2026

ChatFunctions

Model B · Alibaba

Qwen3.8 27B

122.1llmrun Score

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

VisionFunctions

Which should you choose?

Choose Mistral Small 4 119B 2603 if you want…

Longer context window
1M vs 256K tokens
Also does chat
Qwen3.8 27B doesn't list it

Choose Qwen3.8 27B if you want…

Higher llmrun Score
122.1 vs 96.4
Stronger at reasoning
124.0 vs 95.7
Fits a 12 GB GPU
IQ3_XXS · 12 GB; Mistral Small 4 119B 2603 needs 42.8 GB at its smallest quant
Fits a Mac 32 GB
Q4_K_M · 17.9 GB; Mistral Small 4 119B 2603 needs 42.8 GB at its smallest quant
Lighter on memory
17.4 vs 73.2 GB at Q4_K_M
Also does vision
Mistral Small 4 119B 2603 doesn't list it

On your hardware

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

MemoryMistral Small 4 119B 2603Qwen3.8 27B

8 GB

RTX 4060 · 8 GB tier

Mistral Small 4 119B 2603

Doesn't fit

smallest quant needs 42.8 GB

Qwen3.8 27B

Doesn't fit

smallest quant needs 8.8 GB

12 GB

RTX 3060 12GB · 12 GB tier

Mistral Small 4 119B 2603

Doesn't fit

smallest quant needs 42.8 GB

Qwen3.8 27B

IQ3_XXS · ~20 tok/s

12 GB · up to 16Kfits

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Mistral Small 4 119B 2603

Doesn't fit

smallest quant needs 42.8 GB

Qwen3.8 27B

Q3_K_L · ~19 tok/s

15.4 GB · up to 16Kfits

24 GBreference

RTX 4090 · 24 GB tier

Mistral Small 4 119B 2603

Doesn't fit

smallest quant needs 42.8 GB

Qwen3.8 27B

Q4_K_M · ~38 tok/s

17.9 GB · up to 64Kfits

32 GB

RTX 5090 · 32 GB tier

Mistral Small 4 119B 2603

Doesn't fit

smallest quant needs 42.8 GB

Qwen3.8 27B

Q4_K_M · ~67 tok/s

17.9 GB · up to 256Kfits

48 GB

RTX A6000 · 48 GB tier

Mistral Small 4 119B 2603

IQ2_S · ~152 tok/s

47.3 GB · up to 16K

Qwen3.8 27B

Q4_K_M · ~29 tok/s

17.9 GB · up to 256Kmore headroom

Mac 32 GB

Mac Mini M4 · Macs

Mistral Small 4 119B 2603

Doesn't fit

smallest quant needs 42.8 GB

Qwen3.8 27B

Q4_K_M · ~5 tok/s

17.9 GB · up to 128Kfits

Mac 64 GB

Mac Studio M4 Max · Macs

Mistral Small 4 119B 2603

IQ3_XS · ~66 tok/s

59.2 GB · up to 16K

Qwen3.8 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256Kmore headroom

Mac 128 GB

Mac Studio M4 Max · Macs

Mistral Small 4 119B 2603

Q4_K_M · ~54 tok/s

81.6 GB · up to 64Kfaster

Qwen3.8 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256K

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 Small 4 119B 2603 Qwen3.8 27B

Overall

Mistral Small 4 119B 2603

96.489–104

Qwen3.8 27B

122.1120–124

Coding

Mistral Small 4 119B 2603

no data

Qwen3.8 27B

119.7114–125

Agents

Mistral Small 4 119B 2603

no data

Qwen3.8 27B

122.8117–129

Math

Mistral Small 4 119B 2603

no data

Qwen3.8 27B

117.5111–124

Science

Mistral Small 4 119B 2603

no data

Qwen3.8 27B

112.093–131

Reasoning

Mistral Small 4 119B 2603

95.788–104

Qwen3.8 27B

124.0121–127

Mistral Small 4 119B 2603 · #61 of 100 open models · #28 of 60 that fit ≤96 GB

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

Benchmarks

2 shared boards: Mistral Small 4 119B 2603 leads 0, Qwen3.8 27B leads 2 · Benchmarks imported Oct 2026

BoardMistral Small 4 119B 2603Qwen3.8 27B

DTBench

Mistral Small 4 119B 2603

70.9%#32/68 open

Lab-reportedEpoch AI · Mar 2026

Qwen3.8 27B

88.0%#9/68 open

Lab-reportedEpoch AI · Aug 2026

LMCA

Mistral Small 4 119B 2603

20.6%#33/54 open

Lab-reportedEpoch AI · Mar 2026

Qwen3.8 27B

41.4%#7/54 open

Lab-reportedEpoch AI · Aug 2026

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

Only Mistral Small 4 119B 2603 (1)

ALE-Bench497.6

Only Qwen3.8 27B (19)

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 Small 4 119B 2603Qwen3.8 27B

Q2_K

Mistral Small 4 119B 2603

52.3 GB42.1 GB file

32K 70.4 GB · 128K 128 GB

Qwen3.8 27B

12.6 GB10.8 GB file

32K 13.9 GB · 128K 19.3 GB

Q3_K_S

Mistral Small 4 119B 2603

53.8 GB52.0 GB file

32K 71.9 GB · 128K 130 GB

Qwen3.8 27B

12.9 GB12.7 GB file

32K 14.2 GB · 128K 19.6 GB

Q3_K_M

Mistral Small 4 119B 2603

59.7 GB54.6 GB file

32K 77.8 GB · 128K 136 GB

Qwen3.8 27B

14.3 GB13.4 GB file

32K 15.6 GB · 128K 21.0 GB

Q4_0

Mistral Small 4 119B 2603

61.2 GB67.7 GB file

32K 79.3 GB · 128K 137 GB

Qwen3.8 27B

14.6 GB~13.9 GB file

32K 16.0 GB · 128K 21.4 GB

Q4_K_M

Mistral Small 4 119B 2603

73.2 GB72.6 GB file

32K 91.3 GB · 128K 149 GB

Qwen3.8 27B

17.4 GB16.5 GB file

32K 18.8 GB · 128K 24.1 GB

Q5_K_M

Mistral Small 4 119B 2603

86.6 GB85.0 GB file

32K 105 GB · 128K 163 GB

Qwen3.8 27B

20.5 GB19.8 GB file

32K 21.9 GB · 128K 27.3 GB

Q6_K

Mistral Small 4 119B 2603

100 GB102.8 GB file

32K 118 GB · 128K 176 GB

Qwen3.8 27B

23.7 GB22.0 GB file

32K 25.0 GB · 128K 30.4 GB

Q8_0

Mistral Small 4 119B 2603

121 GB126.5 GB file

32K 139 GB · 128K 197 GB

Qwen3.8 27B

28.5 GB29.0 GB file

32K 29.9 GB · 128K 35.2 GB

20 more quants

IQ2_XXS

Mistral Small 4 119B 2603

34.3 GB33.7 GB file

32K 52.5 GB · 128K 110 GB

Qwen3.8 27B

8.4 GB7.3 GB file

32K 9.7 GB · 128K 15.1 GB

IQ2_XS

Mistral Small 4 119B 2603

37.3 GB37.0 GB file

32K 55.5 GB · 128K 113 GB

Qwen3.8 27B

9.1 GB9.1 GB file

32K 10.4 GB · 128K 15.8 GB

IQ2_S

Mistral Small 4 119B 2603

38.8 GB38.1 GB file

32K 56.9 GB · 128K 115 GB

Qwen3.8 27B

9.4 GB8.4 GB file

32K 10.8 GB · 128K 16.1 GB

IQ2_M

Mistral Small 4 119B 2603

41.8 GB41.6 GB file

32K 59.9 GB · 128K 118 GB

Qwen3.8 27B

10.1 GB10.5 GB file

32K 11.5 GB · 128K 16.8 GB

IQ3_XXS

Mistral Small 4 119B 2603

47.8 GB49.9 GB file

32K 65.9 GB · 128K 124 GB

Qwen3.8 27B

11.5 GB10.9 GB file

32K 12.9 GB · 128K 18.2 GB

Q2_K_S

Mistral Small 4 119B 2603

49.3 GB40.4 GB file

32K 67.4 GB · 128K 125 GB

Qwen3.8 27B

not listed

IQ3_XS

Mistral Small 4 119B 2603

50.8 GB51.8 GB file

32K 68.9 GB · 128K 127 GB

Qwen3.8 27B

12.2 GB10.4 GB file

32K 13.6 GB · 128K 18.9 GB

IQ3_S

Mistral Small 4 119B 2603

52.3 GB44.4 GB file

32K 70.4 GB · 128K 128 GB

Qwen3.8 27B

12.6 GB12.0 GB file

32K 13.9 GB · 128K 19.3 GB

IQ3_M

Mistral Small 4 119B 2603

55.2 GB57.0 GB file

32K 73.4 GB · 128K 131 GB

Qwen3.8 27B

13.3 GB14.9 GB file

32K 14.6 GB · 128K 20.0 GB

Q3_K_L

Mistral Small 4 119B 2603

62.7 GB56.9 GB file

32K 80.8 GB · 128K 139 GB

Qwen3.8 27B

15.0 GB14.1 GB file

32K 16.3 GB · 128K 21.7 GB

IQ4_XS

Mistral Small 4 119B 2603

65.7 GB63.8 GB file

32K 83.8 GB · 128K 142 GB

Qwen3.8 27B

15.7 GB14.3 GB file

32K 17.0 GB · 128K 22.4 GB

IQ4_NL

Mistral Small 4 119B 2603

68.7 GB67.5 GB file

32K 86.8 GB · 128K 145 GB

Qwen3.8 27B

16.4 GB17.4 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_1

Mistral Small 4 119B 2603

68.7 GB74.5 GB file

32K 86.8 GB · 128K 145 GB

Qwen3.8 27B

16.4 GB17.5 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_K_S

Mistral Small 4 119B 2603

68.7 GB69.9 GB file

32K 86.8 GB · 128K 145 GB

Qwen3.8 27B

16.4 GB15.4 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_K_L

Mistral Small 4 119B 2603

74.6 GB73.0 GB file

32K 92.8 GB · 128K 151 GB

Qwen3.8 27B

17.8 GB18.8 GB file

32K 19.1 GB · 128K 24.5 GB

Q5_0

Mistral Small 4 119B 2603

76.1 GB81.9 GB file

32K 94.3 GB · 128K 152 GB

Qwen3.8 27B

not listed

Q5_1

Mistral Small 4 119B 2603

83.6 GB89.3 GB file

32K 102 GB · 128K 160 GB

Qwen3.8 27B

not listed

Q5_K_S

Mistral Small 4 119B 2603

83.6 GB82.2 GB file

32K 102 GB · 128K 160 GB

Qwen3.8 27B

19.9 GB18.7 GB file

32K 21.2 GB · 128K 26.6 GB

Q5_K_L

Mistral Small 4 119B 2603

88.1 GB85.4 GB file

32K 106 GB · 128K 164 GB

Qwen3.8 27B

20.9 GB21.5 GB file

32K 22.2 GB · 128K 27.6 GB

BF16

Mistral Small 4 119B 2603

240 GB238.0 GB file

32K 258 GB · 128K 316 GB

Qwen3.8 27B

56.3 GB54.7 GB file

32K 57.7 GB · 128K 63.0 GB

How to run each

Mistral Small 4 119B 2603

Ollama · Q4_K_M

$ollama run hf.co/bartowski/mistralai_Mistral-Small-4-119B-2603-GGUF:Q4_K_M

All ways to run Mistral Small 4 119B 2603 →

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 →

Specifications

Specifications of Mistral Small 4 119B 2603 and Qwen3.8 27B
Spec	Mistral Small 4 119B 2603	Qwen3.8 27B
Publisher	Mistral AI	Alibaba
Parameters	119.4B	27.8B
Active parameters	7.1B per token	—
Architecture	Mistral3ForConditionalGeneration	Qwen3_5ForConditionalGeneration
Context	1M tokens	256K tokens
Modalities	Chat, Function-calling	Vision, Function-calling
License	Apache 2.0	Apache 2.0
Released	Jan 2026	Aug 2026

Frequently Asked Questions

Which is better, Mistral Small 4 119B 2603 or Qwen3.8 27B?

Qwen3.8 27B leads llmrun Score 122.1 to 96.4; only Qwen3.8 27B fits 24 GB (Q4_K_M); Mistral Small 4 119B 2603 needs 42.8 GB even at its smallest quant. Choose Mistral Small 4 119B 2603 for longer context window and also does chat; choose Qwen3.8 27B for higher llmrun Score and stronger at reasoning.

Which needs less VRAM, Mistral Small 4 119B 2603 or Qwen3.8 27B?

At Q4_K_M, Mistral Small 4 119B 2603 requires 73.2 GB while Qwen3.8 27B needs 17.4 GB, making Qwen3.8 27B the easier model to run on your local setup.

Can I run Mistral Small 4 119B 2603 or Qwen3.8 27B on a 16 GB GPU?

Mistral Small 4 119B 2603 does not fit (smallest quant needs 42.8 GB); Qwen3.8 27B fits at Q3_K_L.

Which has a longer context window, Mistral Small 4 119B 2603 or Qwen3.8 27B?

Mistral Small 4 119B 2603 supports 1,048,576 tokens and Qwen3.8 27B supports 262,144 tokens.