Mistral Small 4 119B 2603 vs Qwen3 235B A22B
Qwen3 235B A22B leads llmrun Score 99.6 to 96.4 (ranges overlap); neither fits 24 GB.
Model A · Mistral AI
Mistral Small 4 119B 2603119.4B · 7.1B active · 1M context · Apache 2.0 · Jan 2026
Model B · Alibaba
Qwen3 235B A22B235.1B · 22.2B active · 40K context · Apache 2.0 · Apr 2025
Choose Mistral Small 4 119B 2603 if you want…
Fits a Mac 64 GB
IQ3_XS · 59.2 GB; Qwen3 235B A22B needs 101.8 GB at its smallest quant
Lighter on memory
73.2 vs 141.6 GB at Q4_K_M
Longer context window
1M vs 40K tokens
Newer release
Jan 2026 vs Apr 2025
Choose Qwen3 235B A22B if you want…
Higher llmrun Score
99.6 vs 96.4, ranges overlap
On your hardware
Each model at its default quant (Q4_K_M), a smaller one when it must. Estimates, ±20%.
8 GB
RTX 4060 · 8 GB tier
Mistral Small 4 119B 2603
Doesn't fit
smallest quant needs 42.8 GB
Qwen3 235B A22B
Doesn't fit
smallest quant needs 101.8 GB
12 GB
RTX 3060 12GB · 12 GB tier
Mistral Small 4 119B 2603
Doesn't fit
smallest quant needs 42.8 GB
Qwen3 235B A22B
Doesn't fit
smallest quant needs 101.8 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Mistral Small 4 119B 2603
Doesn't fit
smallest quant needs 42.8 GB
Qwen3 235B A22B
Doesn't fit
smallest quant needs 101.8 GB
24 GBreference
RTX 4090 · 24 GB tier
Mistral Small 4 119B 2603
Doesn't fit
smallest quant needs 42.8 GB
Qwen3 235B A22B
Doesn't fit
smallest quant needs 101.8 GB
32 GB
RTX 5090 · 32 GB tier
Mistral Small 4 119B 2603
Doesn't fit
smallest quant needs 42.8 GB
Qwen3 235B A22B
Doesn't fit
smallest quant needs 101.8 GB
48 GB
RTX A6000 · 48 GB tier
Mistral Small 4 119B 2603
IQ2_S · ~152 tok/s
47.3 GB · up to 16Kfits
Qwen3 235B A22B
Doesn't fit
smallest quant needs 101.8 GB
Mac 32 GB
Mac Mini M4 · Macs
Mistral Small 4 119B 2603
Doesn't fit
smallest quant needs 42.8 GB
Qwen3 235B A22B
Doesn't fit
smallest quant needs 101.8 GB
Mac 64 GB
Mac Studio M4 Max · Macs
Mistral Small 4 119B 2603
IQ3_XS · ~66 tok/s
59.2 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 Small 4 119B 2603
Q4_K_M · ~54 tok/s
81.6 GB · up to 64Kmore 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).
Overall
Mistral Small 4 119B 2603
Qwen3 235B A22B
Coding
Mistral Small 4 119B 2603
no data
Qwen3 235B A22B
Reasoning
Mistral Small 4 119B 2603
Qwen3 235B A22B
Mistral Small 4 119B 2603 · #61 of 100 open models · #28 of 60 that fit ≤96 GB
Qwen3 235B A22B · #52 of 100 open models · #33 of 78 that fit ≤192 GB
Benchmarks
2 shared boards: Mistral Small 4 119B 2603 leads 0, Qwen3 235B A22B leads 2 · Benchmarks imported Oct 2026
10 more boards (other shared and single-model boards)
Only Mistral Small 4 119B 2603 (1)
- ALE-Bench497.6
Only Qwen3 235B A22B (9)
- GPQA Diamond70.7%
- LMArena Text1402.0
- MMLU-Pro68.2%
- Aider Polyglot59.6%
- SimpleBench31.0%
- MATH Level 568.9%
- WeirdML37.3%
- Fiction.LiveBench67.7%
- ForecastBench59.7
VRAM by quantization
Memory to load the model and 2K context; below it, the total at 32K and 128K context. Lighter side in bold.
Q2_K
Mistral Small 4 119B 2603
52.3 GB42.1 GB file
32K 70.4 GB · 128K 128 GB
Qwen3 235B A22B
100 GB85.7 GB file
32K 103 GB · 128K —
Q3_K_S
Mistral Small 4 119B 2603
53.8 GB52.0 GB file
32K 71.9 GB · 128K 130 GB
Qwen3 235B A22B
103 GB101.4 GB file
32K 106 GB · 128K —
Q3_K_M
Mistral Small 4 119B 2603
59.7 GB54.6 GB file
32K 77.8 GB · 128K 136 GB
Qwen3 235B A22B
115 GB112.4 GB file
32K 118 GB · 128K —
Q4_0
Mistral Small 4 119B 2603
61.2 GB67.7 GB file
32K 79.3 GB · 128K 137 GB
Qwen3 235B A22B
not listed
Q4_K_M
Mistral Small 4 119B 2603
73.2 GB72.6 GB file
32K 91.3 GB · 128K 149 GB
Qwen3 235B A22B
142 GB142.2 GB file
32K 145 GB · 128K —
Q5_K_M
Mistral Small 4 119B 2603
86.6 GB85.0 GB file
32K 105 GB · 128K 163 GB
Qwen3 235B A22B
168 GB166.8 GB file
32K 171 GB · 128K —
Q6_K
Mistral Small 4 119B 2603
100 GB102.8 GB file
32K 118 GB · 128K 176 GB
Qwen3 235B A22B
194 GB193.0 GB file
32K 197 GB · 128K —
Q8_0
Mistral Small 4 119B 2603
121 GB126.5 GB file
32K 139 GB · 128K 197 GB
Qwen3 235B A22B
236 GB249.9 GB file
32K 239 GB · 128K —
20 more quants
IQ2_XXS
Mistral Small 4 119B 2603
34.3 GB33.7 GB file
32K 52.5 GB · 128K 110 GB
Qwen3 235B A22B
not listed
IQ2_XS
Mistral Small 4 119B 2603
37.3 GB37.0 GB file
32K 55.5 GB · 128K 113 GB
Qwen3 235B A22B
not listed
IQ2_S
Mistral Small 4 119B 2603
38.8 GB38.1 GB file
32K 56.9 GB · 128K 115 GB
Qwen3 235B A22B
not listed
IQ2_M
Mistral Small 4 119B 2603
41.8 GB41.6 GB file
32K 59.9 GB · 128K 118 GB
Qwen3 235B A22B
not listed
IQ3_XXS
Mistral Small 4 119B 2603
47.8 GB49.9 GB file
32K 65.9 GB · 128K 124 GB
Qwen3 235B A22B
not listed
Q2_K_S
Mistral Small 4 119B 2603
49.3 GB40.4 GB file
32K 67.4 GB · 128K 125 GB
Qwen3 235B A22B
not listed
IQ3_XS
Mistral Small 4 119B 2603
50.8 GB51.8 GB file
32K 68.9 GB · 128K 127 GB
Qwen3 235B A22B
not listed
IQ3_S
Mistral Small 4 119B 2603
52.3 GB44.4 GB file
32K 70.4 GB · 128K 128 GB
Qwen3 235B A22B
not listed
IQ3_M
Mistral Small 4 119B 2603
55.2 GB57.0 GB file
32K 73.4 GB · 128K 131 GB
Qwen3 235B A22B
not listed
Q3_K_L
Mistral Small 4 119B 2603
62.7 GB56.9 GB file
32K 80.8 GB · 128K 139 GB
Qwen3 235B A22B
121 GB111.2 GB file
32K 124 GB · 128K —
IQ4_XS
Mistral Small 4 119B 2603
65.7 GB63.8 GB file
32K 83.8 GB · 128K 142 GB
Qwen3 235B A22B
127 GB125.5 GB file
32K 130 GB · 128K —
IQ4_NL
Mistral Small 4 119B 2603
68.7 GB67.5 GB file
32K 86.8 GB · 128K 145 GB
Qwen3 235B A22B
not listed
Q4_1
Mistral Small 4 119B 2603
68.7 GB74.5 GB file
32K 86.8 GB · 128K 145 GB
Qwen3 235B A22B
133 GB147.2 GB file
32K 136 GB · 128K —
Q4_K_S
Mistral Small 4 119B 2603
68.7 GB69.9 GB file
32K 86.8 GB · 128K 145 GB
Qwen3 235B A22B
133 GB133.7 GB file
32K 136 GB · 128K —
Q4_K_L
Mistral Small 4 119B 2603
74.6 GB73.0 GB file
32K 92.8 GB · 128K 151 GB
Qwen3 235B A22B
not listed
Q5_0
Mistral Small 4 119B 2603
76.1 GB81.9 GB file
32K 94.3 GB · 128K 152 GB
Qwen3 235B A22B
147 GB161.9 GB file
32K 150 GB · 128K —
Q5_1
Mistral Small 4 119B 2603
83.6 GB89.3 GB file
32K 102 GB · 128K 160 GB
Qwen3 235B A22B
not listed
Q5_K_S
Mistral Small 4 119B 2603
83.6 GB82.2 GB file
32K 102 GB · 128K 160 GB
Qwen3 235B A22B
162 GB161.9 GB file
32K 165 GB · 128K —
Q5_K_L
Mistral Small 4 119B 2603
88.1 GB85.4 GB file
32K 106 GB · 128K 164 GB
Qwen3 235B A22B
not listed
BF16
Mistral Small 4 119B 2603
240 GB238.0 GB file
32K 258 GB · 128K 316 GB
Qwen3 235B A22B
471 GB470.3 GB file
32K 474 GB · 128K —
Mistral Small 4 119B 2603
Ollama · Q4_K_M
ollama run hf.co/bartowski/mistralai_Mistral-Small-4-119B-2603-GGUF:Q4_K_MQwen3 235B A22B
Ollama · Q4_K_M
ollama run hf.co/unsloth/Qwen3-235B-A22B-GGUF:Q4_K_M| Spec | Mistral Small 4 119B 2603 | Qwen3 235B A22B |
|---|---|---|
| Publisher | Mistral AI | Alibaba |
| Parameters | 119.4B | 235.1B |
| Active parameters | 7.1B per token | 22B per token |
| Architecture | Mistral3ForConditionalGeneration | Qwen3MoeForCausalLM |
| Context | 1M tokens | 40K tokens |
| Modalities | Chat, Function-calling | Chat, Function-calling |
| License | Apache 2.0 | Apache 2.0 |
| Released | Jan 2026 | Apr 2025 |
Frequently Asked Questions
Which is better, Mistral Small 4 119B 2603 or Qwen3 235B A22B?
Qwen3 235B A22B leads llmrun Score 99.6 to 96.4 (ranges overlap); neither fits 24 GB. Choose Mistral Small 4 119B 2603 for fits a Mac 64 GB and lighter on memory; choose Qwen3 235B A22B for higher llmrun Score.
Which needs less VRAM, Mistral Small 4 119B 2603 or Qwen3 235B A22B?
At Q4_K_M, Mistral Small 4 119B 2603 requires 73.2 GB while Qwen3 235B A22B needs 141.6 GB, making Mistral Small 4 119B 2603 the easier model to run on your local setup.
Can I run Mistral Small 4 119B 2603 or Qwen3 235B A22B on a 16 GB GPU?
Mistral Small 4 119B 2603 does not fit (smallest quant needs 42.8 GB); Qwen3 235B A22B does not fit (smallest quant needs 101.8 GB).
Which has a longer context window, Mistral Small 4 119B 2603 or Qwen3 235B A22B?
Mistral Small 4 119B 2603 supports 1,048,576 tokens and Qwen3 235B A22B supports 40,960 tokens.