Magistral Small 2509 vs Mistral Small 3.2 24B Instruct 2506
Magistral Small 2509 and Mistral Small 3.2 24B Instruct 2506 match in llmrun Score, with values of 85.5 versus 85.6; both fit 24 GB at Q4_K_M.
Model A · Mistral AI
Magistral Small 250924.0B · 128K context · Apache 2.0 · Sep 2025
Model B · Mistral AI
Mistral Small 3.2 24B Instruct 250624.0B · 128K context · Apache 2.0 · Jun 2025
Choose Magistral Small 2509 if you want…
Ahead on the benchmarks
4 of 6 shared boards
Mistral Small 3.2 24B Instruct 2506: no clear edge over Magistral Small 2509 in the data we have.
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
Magistral Small 2509
Doesn't fit
smallest quant needs 10.3 GB
Mistral Small 3.2 24B Instruct 2506
Doesn't fit
smallest quant needs 10.3 GB
12 GB
RTX 3060 12GB · 12 GB tier
Magistral Small 2509
IQ2_M · ~27 tok/s
11.8 GB · up to 16K
Mistral Small 3.2 24B Instruct 2506
IQ2_M · ~27 tok/s
11.8 GB · up to 16K
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Magistral Small 2509
Q4_K_M · ~19 tok/stight
18.1 GB · up to 4K
Mistral Small 3.2 24B Instruct 2506
Q4_K_M · ~19 tok/stight
18.1 GB · up to 4K
24 GBreference
RTX 4090 · 24 GB tier
Magistral Small 2509
Q4_K_M · ~43 tok/s
18.1 GB · up to 32K
Mistral Small 3.2 24B Instruct 2506
Q4_K_M · ~43 tok/s
18.1 GB · up to 32K
32 GB
RTX 5090 · 32 GB tier
Magistral Small 2509
Q4_K_M · ~77 tok/s
18.1 GB · up to 64K
Mistral Small 3.2 24B Instruct 2506
Q4_K_M · ~77 tok/s
18.1 GB · up to 64K
48 GB
RTX A6000 · 48 GB tier
Magistral Small 2509
Q4_K_M · ~33 tok/s
18.1 GB · up to 128K
Mistral Small 3.2 24B Instruct 2506
Q4_K_M · ~33 tok/s
18.1 GB · up to 128K
Mac 32 GB
Mac Mini M4 · Macs
Magistral Small 2509
Q4_K_M · ~6 tok/s
18.1 GB · up to 64K
Mistral Small 3.2 24B Instruct 2506
Q4_K_M · ~6 tok/s
18.1 GB · up to 64K
Mac 64 GB
Mac Studio M4 Max · Macs
Magistral Small 2509
Q4_K_M · ~25 tok/s
18.1 GB · up to 128K
Mistral Small 3.2 24B Instruct 2506
Q4_K_M · ~25 tok/s
18.1 GB · up to 128K
Mac 128 GB
Mac Studio M4 Max · Macs
Magistral Small 2509
Q4_K_M · ~25 tok/s
18.1 GB · up to 128K
Mistral Small 3.2 24B Instruct 2506
Q4_K_M · ~25 tok/s
18.1 GB · up to 128K
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
Magistral Small 2509
Mistral Small 3.2 24B Instruct 2506
Science
Magistral Small 2509
Mistral Small 3.2 24B Instruct 2506
Reasoning
Magistral Small 2509
Mistral Small 3.2 24B Instruct 2506
Magistral Small 2509 · #69 of 92 open models · #21 of 34 that fit 24 GB
Mistral Small 3.2 24B Instruct 2506 · #68 of 92 open models · #20 of 34 that fit 24 GB
Benchmarks
6 shared boards: Magistral Small 2509 leads 4, Mistral Small 3.2 24B Instruct 2506 leads 2 · Benchmarks imported Oct 2026
Magistral Small 2509
47.6%#57/97 open
IndependentEpoch AI · Sep 2025
Mistral Small 3.2 24B Instruct 2506
49.0%#54/97 open
IndependentEpoch AI · Jun 2025
Magistral Small 2509
28.1%#50/85 open
IndependentEpoch AI · Sep 2025
Mistral Small 3.2 24B Instruct 2506
30.3%#48/85 open
IndependentEpoch AI · Jun 2025
Magistral Small 2509
35.2%#46/65 open
Lab-reportedEpoch AI · Sep 2025
Mistral Small 3.2 24B Instruct 2506
26.4%#56/65 open
Lab-reportedEpoch AI · Jun 2025
Magistral Small 2509
3.0%#38/67 open
IndependentEpoch AI · Sep 2025
Mistral Small 3.2 24B Instruct 2506
1.0%#44/67 open
IndependentEpoch AI · Jun 2025
Magistral Small 2509
0.3%#40/65 open
Lab-reportedEpoch AI · Sep 2025
Mistral Small 3.2 24B Instruct 2506
0.0%#60/65 open
Lab-reportedEpoch AI · Jun 2025
Magistral Small 2509
61.3%#44/68 open
Lab-reportedEpoch AI · Sep 2025
Mistral Small 3.2 24B Instruct 2506
59.9%#49/68 open
Lab-reportedEpoch AI · Jun 2025
1 more board (other shared and single-model boards)
Only Mistral Small 3.2 24B Instruct 2506 (1)
- LMArena Text1356.2
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
Magistral Small 2509
10.9 GB8.9 GB file
32K 17.2 GB · 128K 37.3 GB
Mistral Small 3.2 24B Instruct 2506
10.9 GB8.9 GB file
32K 17.2 GB · 128K 37.3 GB
Q3_K_S
Magistral Small 2509
11.2 GB10.4 GB file
32K 17.5 GB · 128K 37.6 GB
Mistral Small 3.2 24B Instruct 2506
11.2 GB10.4 GB file
32K 17.5 GB · 128K 37.6 GB
Q3_K_M
Magistral Small 2509
12.4 GB11.5 GB file
32K 18.7 GB · 128K 38.8 GB
Mistral Small 3.2 24B Instruct 2506
12.4 GB11.5 GB file
32K 18.7 GB · 128K 38.8 GB
Q4_0
Magistral Small 2509
12.7 GB13.5 GB file
32K 19.0 GB · 128K 39.2 GB
Mistral Small 3.2 24B Instruct 2506
12.7 GB13.5 GB file
32K 19.0 GB · 128K 39.2 GB
Q4_K_M
Magistral Small 2509
15.1 GB14.3 GB file
32K 21.4 GB · 128K 41.6 GB
Mistral Small 3.2 24B Instruct 2506
15.1 GB14.3 GB file
32K 21.4 GB · 128K 41.6 GB
Q5_K_M
Magistral Small 2509
17.8 GB16.8 GB file
32K 24.1 GB · 128K 44.3 GB
Mistral Small 3.2 24B Instruct 2506
17.8 GB16.8 GB file
32K 24.1 GB · 128K 44.3 GB
Q6_K
Magistral Small 2509
20.5 GB19.3 GB file
32K 26.8 GB · 128K 47.0 GB
Mistral Small 3.2 24B Instruct 2506
20.5 GB19.3 GB file
32K 26.8 GB · 128K 47.0 GB
Q8_0
Magistral Small 2509
24.7 GB25.1 GB file
32K 31.0 GB · 128K 51.2 GB
Mistral Small 3.2 24B Instruct 2506
24.7 GB25.1 GB file
32K 31.0 GB · 128K 51.2 GB
19 more quants
IQ2_XXS
Magistral Small 2509
7.3 GB6.8 GB file
32K 13.6 GB · 128K 33.7 GB
Mistral Small 3.2 24B Instruct 2506
7.3 GB6.8 GB file
32K 13.6 GB · 128K 33.7 GB
IQ2_XS
Magistral Small 2509
7.9 GB7.2 GB file
32K 14.2 GB · 128K 34.3 GB
Mistral Small 3.2 24B Instruct 2506
7.9 GB7.2 GB file
32K 14.2 GB · 128K 34.3 GB
IQ2_S
Magistral Small 2509
8.2 GB7.5 GB file
32K 14.5 GB · 128K 34.6 GB
Mistral Small 3.2 24B Instruct 2506
8.2 GB7.5 GB file
32K 14.5 GB · 128K 34.6 GB
IQ2_M
Magistral Small 2509
8.8 GB8.2 GB file
32K 15.1 GB · 128K 35.2 GB
Mistral Small 3.2 24B Instruct 2506
8.8 GB8.2 GB file
32K 15.1 GB · 128K 35.2 GB
IQ3_XXS
Magistral Small 2509
10.0 GB9.4 GB file
32K 16.3 GB · 128K 36.4 GB
Mistral Small 3.2 24B Instruct 2506
10.0 GB9.4 GB file
32K 16.3 GB · 128K 36.4 GB
Q2_K_S
Magistral Small 2509
not listed
Mistral Small 3.2 24B Instruct 2506
10.3 GB8.3 GB file
32K 16.6 GB · 128K 36.7 GB
IQ3_XS
Magistral Small 2509
10.6 GB9.9 GB file
32K 16.9 GB · 128K 37.0 GB
Mistral Small 3.2 24B Instruct 2506
10.6 GB9.9 GB file
32K 16.9 GB · 128K 37.0 GB
IQ3_S
Magistral Small 2509
not listed
Mistral Small 3.2 24B Instruct 2506
10.9 GB10.4 GB file
32K 17.2 GB · 128K 37.3 GB
IQ3_M
Magistral Small 2509
11.5 GB10.7 GB file
32K 17.8 GB · 128K 37.9 GB
Mistral Small 3.2 24B Instruct 2506
11.5 GB10.7 GB file
32K 17.8 GB · 128K 37.9 GB
Q3_K_L
Magistral Small 2509
13.0 GB12.4 GB file
32K 19.3 GB · 128K 39.5 GB
Mistral Small 3.2 24B Instruct 2506
13.0 GB12.4 GB file
32K 19.3 GB · 128K 39.5 GB
IQ4_XS
Magistral Small 2509
13.6 GB12.8 GB file
32K 19.9 GB · 128K 40.1 GB
Mistral Small 3.2 24B Instruct 2506
13.6 GB12.8 GB file
32K 19.9 GB · 128K 40.1 GB
IQ4_NL
Magistral Small 2509
14.2 GB13.5 GB file
32K 20.5 GB · 128K 40.7 GB
Mistral Small 3.2 24B Instruct 2506
14.2 GB13.5 GB file
32K 20.5 GB · 128K 40.7 GB
Q4_1
Magistral Small 2509
14.2 GB14.9 GB file
32K 20.5 GB · 128K 40.7 GB
Mistral Small 3.2 24B Instruct 2506
14.2 GB14.9 GB file
32K 20.5 GB · 128K 40.7 GB
Q4_K_S
Magistral Small 2509
14.2 GB13.5 GB file
32K 20.5 GB · 128K 40.7 GB
Mistral Small 3.2 24B Instruct 2506
14.2 GB13.5 GB file
32K 20.5 GB · 128K 40.7 GB
Q4_K_L
Magistral Small 2509
15.4 GB14.8 GB file
32K 21.7 GB · 128K 41.9 GB
Mistral Small 3.2 24B Instruct 2506
15.4 GB14.8 GB file
32K 21.7 GB · 128K 41.9 GB
Q5_0
Magistral Small 2509
not listed
Mistral Small 3.2 24B Instruct 2506
15.7 GB16.4 GB file
32K 22.0 GB · 128K 42.2 GB
Q5_K_S
Magistral Small 2509
17.2 GB16.3 GB file
32K 23.5 GB · 128K 43.7 GB
Mistral Small 3.2 24B Instruct 2506
17.2 GB16.3 GB file
32K 23.5 GB · 128K 43.7 GB
Q5_K_L
Magistral Small 2509
18.1 GB17.2 GB file
32K 24.4 GB · 128K 44.6 GB
Mistral Small 3.2 24B Instruct 2506
18.1 GB17.2 GB file
32K 24.4 GB · 128K 44.6 GB
BF16
Magistral Small 2509
48.7 GB47.2 GB file
32K 55.0 GB · 128K 75.2 GB
Mistral Small 3.2 24B Instruct 2506
48.7 GB47.2 GB file
32K 55.0 GB · 128K 75.2 GB
Magistral Small 2509
Ollama · Q4_K_M
ollama run hf.co/unsloth/Magistral-Small-2509-GGUF:Q4_K_MMistral Small 3.2 24B Instruct 2506
Ollama · Q4_K_M
ollama run hf.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF:Q4_K_M| Spec | Magistral Small 2509 | Mistral Small 3.2 24B Instruct 2506 |
|---|---|---|
| Publisher | Mistral AI | Mistral AI |
| Parameters | 24.0B | 24.0B |
| Architecture | Mistral3ForConditionalGeneration | Mistral3ForConditionalGeneration |
| Context | 128K tokens | 128K tokens |
| Modalities | Chat | Chat |
| License | Apache 2.0 | Apache 2.0 |
| Released | Sep 2025 | Jun 2025 |
Frequently Asked Questions
Which is better, Magistral Small 2509 or Mistral Small 3.2 24B Instruct 2506?
Magistral Small 2509 and Mistral Small 3.2 24B Instruct 2506 match in llmrun Score, with values of 85.5 versus 85.6; both fit 24 GB at Q4_K_M. Choose Magistral Small 2509 for ahead on the benchmarks.
Which needs less VRAM, Magistral Small 2509 or Mistral Small 3.2 24B Instruct 2506?
At Q4_K_M, Magistral Small 2509 requires 15.1 GB while Mistral Small 3.2 24B Instruct 2506 needs 15.1 GB, making Magistral Small 2509 the easier model to run on your local setup.
Which is faster on RTX 4090?
Estimated decode speed on RTX 4090 is about 43 tok/s for Magistral Small 2509 (Q4_K_M) and 43 tok/s for Mistral Small 3.2 24B Instruct 2506 (Q4_K_M), so Magistral Small 2509 is faster. Estimates, ±20%.
Can I run Magistral Small 2509 or Mistral Small 3.2 24B Instruct 2506 on a 16 GB GPU?
Magistral Small 2509 fits at Q4_K_M; Mistral Small 3.2 24B Instruct 2506 fits at Q4_K_M.
Which has a longer context window, Magistral Small 2509 or Mistral Small 3.2 24B Instruct 2506?
Magistral Small 2509 supports 131,072 tokens and Mistral Small 3.2 24B Instruct 2506 supports 131,072 tokens.