Mistral Medium 3.5 128B vs Qwen3 235B A22B

Mistral Medium 3.5 128B leads llmrun Score 102.1 to 100.0 (ranges overlap); 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

Qwen3 235B A22B

100.0llmrun Score

235.1B · 22.2B active · 40K context · Apache 2.0 · Apr 2025

ChatFunctions

Which should you choose?

Choose Mistral Medium 3.5 128B if you want…

Higher llmrun Score
102.1 vs 100.0, ranges overlap
Ahead on the benchmarks
2 of 3 shared boards
Fits a Mac 64 GB
IQ3_S · 60.5 GB; Qwen3 235B A22B needs 101.8 GB at its smallest quant
Lighter on memory
77.7 vs 141.6 GB at Q4_K_M
Longer context window
256K vs 40K tokens
Newer release
Mar 2026 vs Apr 2025

Choose Qwen3 235B A22B if you want…

More permissive license
Apache 2.0 vs Other

On your hardware

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

MemoryMistral Medium 3.5 128BQwen3 235B A22B

8 GB

RTX 4060 · 8 GB tier

Mistral Medium 3.5 128B

Doesn't fit

smallest quant needs 41.3 GB

Qwen3 235B A22B

Doesn't fit

smallest quant needs 101.8 GB

12 GB

RTX 3060 12GB · 12 GB tier

Mistral Medium 3.5 128B

Doesn't fit

smallest quant needs 41.3 GB

Qwen3 235B A22B

Doesn't fit

smallest quant needs 101.8 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Mistral Medium 3.5 128B

Doesn't fit

smallest quant needs 41.3 GB

Qwen3 235B A22B

Doesn't fit

smallest quant needs 101.8 GB

24 GBreference

RTX 4090 · 24 GB tier

Mistral Medium 3.5 128B

Doesn't fit

smallest quant needs 41.3 GB

Qwen3 235B A22B

Doesn't fit

smallest quant needs 101.8 GB

32 GB

RTX 5090 · 32 GB tier

Mistral Medium 3.5 128B

Doesn't fit

smallest quant needs 41.3 GB

Qwen3 235B A22B

Doesn't fit

smallest quant needs 101.8 GB

48 GB

RTX A6000 · 48 GB tier

Mistral Medium 3.5 128B

IQ2_S · ~12 tok/s

46.1 GB · up to 16Kfits

Qwen3 235B A22B

Doesn't fit

smallest quant needs 101.8 GB

Mac 32 GB

Mac Mini M4 · Macs

Mistral Medium 3.5 128B

Doesn't fit

smallest quant needs 41.3 GB

Qwen3 235B A22B

Doesn't fit

smallest quant needs 101.8 GB

Mac 64 GB

Mac Studio M4 Max · Macs

Mistral Medium 3.5 128B

IQ3_S · ~7 tok/s

60.5 GB · up to 16Kfits

Qwen3 235B A22B

Doesn't fit

smallest quant needs 101.8 GB

Mac 128 GB

Mac Studio M4 Max · Macs

Mistral Medium 3.5 128B

Q4_K_M · ~5 tok/s

82.8 GB · up to 128Kmore headroom

Qwen3 235B A22B

Q3_K_L · ~21 tok/s

122.4 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

Mistral Medium 3.5 128B Qwen3 235B A22B

Overall

Mistral Medium 3.5 128B

102.197–107

Qwen3 235B A22B

100.097–103

Coding

Mistral Medium 3.5 128B

102.296–108

Qwen3 235B A22B

101.396–107

Science

Mistral Medium 3.5 128B

101.380–123

Qwen3 235B A22B

no data

Reasoning

Mistral Medium 3.5 128B

101.593–110

Qwen3 235B A22B

100.894–108

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

Qwen3 235B A22B · #58 of 106 open models · #36 of 82 that fit ≤192 GB

Benchmarks

3 shared boards: Mistral Medium 3.5 128B leads 2, Qwen3 235B A22B leads 0 · Benchmarks imported Nov 2026

BoardMistral Medium 3.5 128BQwen3 235B A22B

WeirdML

Mistral Medium 3.5 128B

43.7%#16/47 open

IndependentEpoch AI · Apr 2026

Qwen3 235B A22B

37.3%#30/47 open

IndependentEpoch AI · Apr 2025

DTBench

Mistral Medium 3.5 128B

75.5%#30/70 open

Lab-reportedEpoch AI · Apr 2026

Qwen3 235B A22B

75.7%#29/70 open

Lab-reportedEpoch AI · Apr 2025

LMCA

Mistral Medium 3.5 128B

26.1%#28/56 open

Lab-reportedEpoch AI · Apr 2026

Qwen3 235B A22B

25.0%#29/56 open

Lab-reportedEpoch AI · Apr 2025

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

LMArena Text

Mistral Medium 3.5 128B

1426.4#28/188 open

ArenaLMArena · Oct 2026

Qwen3 235B A22B

1402.1#48/188 open

ArenaLMArena · Oct 2026

Only Mistral Medium 3.5 128B (7)

Only Qwen3 235B A22B (7)

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 128BQwen3 235B A22B

Q2_K

Mistral Medium 3.5 128B

55.3 GB46.6 GB file

32K 66.4 GB · 128K 102 GB

Qwen3 235B A22B

100 GB85.7 GB file

32K 103 GB · 128K —

Q3_K_S

Mistral Medium 3.5 128B

56.9 GB54.4 GB file

32K 68.0 GB · 128K 103 GB

Qwen3 235B A22B

103 GB101.4 GB file

32K 106 GB · 128K —

Q3_K_M

Mistral Medium 3.5 128B

63.3 GB60.6 GB file

32K 74.4 GB · 128K 110 GB

Qwen3 235B A22B

115 GB112.4 GB file

32K 118 GB · 128K —

Q4_0

Mistral Medium 3.5 128B

64.9 GB71.0 GB file

32K 76.0 GB · 128K 111 GB

Qwen3 235B A22B

not listed

Q4_K_M

Mistral Medium 3.5 128B

77.7 GB74.9 GB file

32K 88.7 GB · 128K 124 GB

Qwen3 235B A22B

142 GB142.2 GB file

32K 145 GB · 128K —

Q5_K_M

Mistral Medium 3.5 128B

92.0 GB88.3 GB file

32K 103 GB · 128K 139 GB

Qwen3 235B A22B

168 GB166.8 GB file

32K 171 GB · 128K —

Q6_K

Mistral Medium 3.5 128B

106 GB102.6 GB file

32K 117 GB · 128K 153 GB

Qwen3 235B A22B

194 GB193.0 GB file

32K 197 GB · 128K —

Q8_0

Mistral Medium 3.5 128B

129 GB132.9 GB file

32K 140 GB · 128K 175 GB

Qwen3 235B A22B

236 GB249.9 GB file

32K 239 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

Qwen3 235B A22B

not listed

IQ2_XS

Mistral Medium 3.5 128B

39.4 GB43.4 GB file

32K 50.4 GB · 128K 85.9 GB

Qwen3 235B A22B

not listed

IQ2_S

Mistral Medium 3.5 128B

41.0 GB46.1 GB file

32K 52.0 GB · 128K 87.5 GB

Qwen3 235B A22B

not listed

IQ2_M

Mistral Medium 3.5 128B

44.1 GB44.1 GB file

32K 55.2 GB · 128K 90.7 GB

Qwen3 235B A22B

not listed

IQ3_XXS

Mistral Medium 3.5 128B

50.5 GB49.3 GB file

32K 61.6 GB · 128K 97.0 GB

Qwen3 235B A22B

not listed

Q2_K_S

Mistral Medium 3.5 128B

52.1 GB43.0 GB file

32K 63.2 GB · 128K 98.6 GB

Qwen3 235B A22B

not listed

IQ3_XS

Mistral Medium 3.5 128B

53.7 GB54.9 GB file

32K 64.8 GB · 128K 100 GB

Qwen3 235B A22B

not listed

IQ3_S

Mistral Medium 3.5 128B

55.3 GB54.5 GB file

32K 66.4 GB · 128K 102 GB

Qwen3 235B A22B

not listed

IQ3_M

Mistral Medium 3.5 128B

58.5 GB59.5 GB file

32K 69.6 GB · 128K 105 GB

Qwen3 235B A22B

not listed

Q3_K_L

Mistral Medium 3.5 128B

66.5 GB67.0 GB file

32K 77.6 GB · 128K 113 GB

Qwen3 235B A22B

121 GB111.2 GB file

32K 124 GB · 128K —

IQ4_XS

Mistral Medium 3.5 128B

69.7 GB67.1 GB file

32K 80.8 GB · 128K 116 GB

Qwen3 235B A22B

127 GB125.5 GB file

32K 130 GB · 128K —

IQ4_NL

Mistral Medium 3.5 128B

72.9 GB70.9 GB file

32K 83.9 GB · 128K 119 GB

Qwen3 235B A22B

not listed

Q4_1

Mistral Medium 3.5 128B

72.9 GB78.5 GB file

32K 83.9 GB · 128K 119 GB

Qwen3 235B A22B

133 GB147.2 GB file

32K 136 GB · 128K —

Q4_K_S

Mistral Medium 3.5 128B

72.9 GB71.2 GB file

32K 83.9 GB · 128K 119 GB

Qwen3 235B A22B

133 GB133.7 GB file

32K 136 GB · 128K —

Q4_K_L

Mistral Medium 3.5 128B

79.3 GB79.6 GB file

32K 90.3 GB · 128K 126 GB

Qwen3 235B A22B

not listed

Q5_0

Mistral Medium 3.5 128B

not listed

Qwen3 235B A22B

147 GB161.9 GB file

32K 150 GB · 128K —

Q5_K_S

Mistral Medium 3.5 128B

88.8 GB86.2 GB file

32K 99.9 GB · 128K 135 GB

Qwen3 235B A22B

162 GB161.9 GB file

32K 165 GB · 128K —

Q5_K_L

Mistral Medium 3.5 128B

93.6 GB92.1 GB file

32K 105 GB · 128K 140 GB

Qwen3 235B A22B

not listed

BF16

Mistral Medium 3.5 128B

256 GB250.1 GB file

32K 268 GB · 128K 303 GB

Qwen3 235B A22B

471 GB470.3 GB file

32K 474 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 →

Qwen3 235B A22B

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Qwen3-235B-A22B-GGUF:Q4_K_M

All ways to run Qwen3 235B A22B →

Specifications

Specifications of Mistral Medium 3.5 128B and Qwen3 235B A22B
Spec	Mistral Medium 3.5 128B	Qwen3 235B A22B
Publisher	Mistral AI	Alibaba
Parameters	127.7B	235.1B
Active parameters	—	22B per token
Architecture	Mistral3ForConditionalGeneration	Qwen3MoeForCausalLM
Context	256K tokens	40K tokens
Modalities	Chat, Function-calling	Chat, Function-calling
License	Other	Apache 2.0
Released	Mar 2026	Apr 2025

Frequently Asked Questions

Which is better, Mistral Medium 3.5 128B or Qwen3 235B A22B?

Mistral Medium 3.5 128B leads llmrun Score 102.1 to 100.0 (ranges overlap); neither fits 24 GB. Choose Mistral Medium 3.5 128B for higher llmrun Score and ahead on the benchmarks; choose Qwen3 235B A22B for more permissive license.

Which needs less VRAM, Mistral Medium 3.5 128B or Qwen3 235B A22B?

At Q4_K_M, Mistral Medium 3.5 128B requires 77.7 GB while Qwen3 235B A22B needs 141.6 GB, making Mistral Medium 3.5 128B the easier model to run on your local setup.

Can I run Mistral Medium 3.5 128B or Qwen3 235B A22B on a 16 GB GPU?

Mistral Medium 3.5 128B does not fit (smallest quant needs 41.3 GB); Qwen3 235B A22B does not fit (smallest quant needs 101.8 GB).

Which has a longer context window, Mistral Medium 3.5 128B or Qwen3 235B A22B?

Mistral Medium 3.5 128B supports 262,144 tokens and Qwen3 235B A22B supports 40,960 tokens.