Phi 4 vs Magistral Small 2509
Phi 4 and Magistral Small 2509 match in llmrun Score, with values of 83.8 versus 85.5; both fit 24 GB at Q4_K_M; Phi 4 is 1.6× faster on RTX 4090 (~69 vs ~43 tok/s).
Model B · Mistral AI
Magistral Small 250924.0B · 128K context · Apache 2.0 · Sep 2025
Choose Phi 4 if you want…
Fits a 12 GB GPU
Q4_K_M · 12.5 GB; Magistral Small 2509 needs 10.3 GB at its smallest quant
1.6× faster on RTX 4090
~69 vs ~43 tok/s
Lighter on memory
9.5 vs 15.1 GB at Q4_K_M
Also does math, code
Magistral Small 2509 doesn't list it
Choose Magistral Small 2509 if you want…
Longer context window
128K vs 16K tokens
Newer release
Sep 2025 vs Dec 2024
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
Phi 4
IQ2_XXS · ~37 tok/s
7.7 GB · up to 16Kfits
Magistral Small 2509
Doesn't fit
smallest quant needs 10.3 GB
12 GB
RTX 3060 12GB · 12 GB tier
Phi 4
Q4_K_M · ~25 tok/stight
12.5 GB · up to 8K
Magistral Small 2509
IQ2_M · ~27 tok/s
11.8 GB · up to 16Kmore headroom
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Phi 4
Q4_K_M · ~31 tok/s
12.5 GB · up to 16Kmore headroom
Magistral Small 2509
Q4_K_M · ~19 tok/stight
18.1 GB · up to 4K
24 GBreference
RTX 4090 · 24 GB tier
Phi 4
Q4_K_M · ~69 tok/s
12.5 GB · up to 16Kfaster
Magistral Small 2509
Q4_K_M · ~43 tok/s
18.1 GB · up to 32K
32 GB
RTX 5090 · 32 GB tier
Phi 4
Q4_K_M · ~122 tok/s
12.5 GB · up to 16Kfaster
Magistral Small 2509
Q4_K_M · ~77 tok/s
18.1 GB · up to 64K
48 GB
RTX A6000 · 48 GB tier
Phi 4
Q4_K_M · ~52 tok/s
12.5 GB · up to 16Kfaster
Magistral Small 2509
Q4_K_M · ~33 tok/s
18.1 GB · up to 128K
Mac 32 GB
Mac Mini M4 · Macs
Phi 4
Q4_K_M · ~9 tok/s
12.5 GB · up to 16Kfaster
Magistral Small 2509
Q4_K_M · ~6 tok/s
18.1 GB · up to 64K
Mac 64 GB
Mac Studio M4 Max · Macs
Phi 4
Q4_K_M · ~40 tok/s
12.5 GB · up to 16Kfaster
Magistral Small 2509
Q4_K_M · ~25 tok/s
18.1 GB · up to 128K
Mac 128 GB
Mac Studio M4 Max · Macs
Phi 4
Q4_K_M · ~40 tok/s
12.5 GB · up to 16Kfaster
Magistral Small 2509
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
Phi 4
Magistral Small 2509
Science
Phi 4
no data
Magistral Small 2509
Reasoning
Phi 4
no data
Magistral Small 2509
Phi 4 · #70 of 92 open models · #22 of 34 that fit 24 GB
Magistral Small 2509 · #69 of 92 open models · #21 of 34 that fit 24 GB
Benchmarks
3 shared boards: Phi 4 leads 1, Magistral Small 2509 leads 2 · Benchmarks imported Oct 2026
Phi 4
56.1%#45/97 open
IndependentEpoch AI · Dec 2024
Magistral Small 2509
47.6%#57/97 open
IndependentEpoch AI · Sep 2025
Phi 4
13.8%#56/85 open
IndependentEpoch AI · Dec 2024
Magistral Small 2509
28.1%#50/85 open
IndependentEpoch AI · Sep 2025
Phi 4
1.0%#42/67 open
IndependentEpoch AI · Dec 2024
Magistral Small 2509
3.0%#38/67 open
IndependentEpoch AI · Sep 2025
8 more boards (other shared and single-model boards)
Only Phi 4 (5)
- LMArena Text1256.3
- MMLU-Pro70.4%
- MATH Level 564.9%
- MMLU84.8%
- BALROG11.6%
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
Phi 4
7.0 GB5.5 GB file
32K — · 128K —
Magistral Small 2509
10.9 GB8.9 GB file
32K 17.2 GB · 128K 37.3 GB
Q3_K_S
Phi 4
7.1 GB6.5 GB file
32K — · 128K —
Magistral Small 2509
11.2 GB10.4 GB file
32K 17.5 GB · 128K 37.6 GB
Q3_K_M
Phi 4
7.9 GB7.4 GB file
32K — · 128K —
Magistral Small 2509
12.4 GB11.5 GB file
32K 18.7 GB · 128K 38.8 GB
Q4_0
Phi 4
8.1 GB8.4 GB file
32K — · 128K —
Magistral Small 2509
12.7 GB13.5 GB file
32K 19.0 GB · 128K 39.2 GB
Q4_K_M
Phi 4
9.5 GB9.1 GB file
32K — · 128K —
Magistral Small 2509
15.1 GB14.3 GB file
32K 21.4 GB · 128K 41.6 GB
Q5_K_M
Phi 4
11.2 GB10.6 GB file
32K — · 128K —
Magistral Small 2509
17.8 GB16.8 GB file
32K 24.1 GB · 128K 44.3 GB
Q6_K
Phi 4
12.8 GB12.0 GB file
32K — · 128K —
Magistral Small 2509
20.5 GB19.3 GB file
32K 26.8 GB · 128K 47.0 GB
Q8_0
Phi 4
15.4 GB15.6 GB file
32K — · 128K —
Magistral Small 2509
24.7 GB25.1 GB file
32K 31.0 GB · 128K 51.2 GB
19 more quants
IQ2_XXS
Phi 4
4.8 GB4.1 GB file
32K — · 128K —
Magistral Small 2509
7.3 GB6.8 GB file
32K 13.6 GB · 128K 33.7 GB
IQ2_XS
Phi 4
5.1 GB4.5 GB file
32K — · 128K —
Magistral Small 2509
7.9 GB7.2 GB file
32K 14.2 GB · 128K 34.3 GB
IQ2_S
Phi 4
5.3 GB4.7 GB file
32K — · 128K —
Magistral Small 2509
8.2 GB7.5 GB file
32K 14.5 GB · 128K 34.6 GB
IQ2_M
Phi 4
5.7 GB5.1 GB file
32K — · 128K —
Magistral Small 2509
8.8 GB8.2 GB file
32K 15.1 GB · 128K 35.2 GB
IQ3_XXS
Phi 4
6.4 GB5.8 GB file
32K — · 128K —
Magistral Small 2509
10.0 GB9.4 GB file
32K 16.3 GB · 128K 36.4 GB
Q2_K_S
Phi 4
6.6 GB5.2 GB file
32K — · 128K —
Magistral Small 2509
not listed
IQ3_XS
Phi 4
6.8 GB6.2 GB file
32K — · 128K —
Magistral Small 2509
10.6 GB9.9 GB file
32K 16.9 GB · 128K 37.0 GB
IQ3_S
Phi 4
7.0 GB6.5 GB file
32K — · 128K —
Magistral Small 2509
not listed
IQ3_M
Phi 4
7.3 GB6.9 GB file
32K — · 128K —
Magistral Small 2509
11.5 GB10.7 GB file
32K 17.8 GB · 128K 37.9 GB
Q3_K_L
Phi 4
8.2 GB7.9 GB file
32K — · 128K —
Magistral Small 2509
13.0 GB12.4 GB file
32K 19.3 GB · 128K 39.5 GB
IQ4_XS
Phi 4
8.6 GB7.9 GB file
32K — · 128K —
Magistral Small 2509
13.6 GB12.8 GB file
32K 19.9 GB · 128K 40.1 GB
IQ4_NL
Phi 4
9.0 GB8.4 GB file
32K — · 128K —
Magistral Small 2509
14.2 GB13.5 GB file
32K 20.5 GB · 128K 40.7 GB
Q4_1
Phi 4
9.0 GB9.3 GB file
32K — · 128K —
Magistral Small 2509
14.2 GB14.9 GB file
32K 20.5 GB · 128K 40.7 GB
Q4_K_S
Phi 4
9.0 GB8.4 GB file
32K — · 128K —
Magistral Small 2509
14.2 GB13.5 GB file
32K 20.5 GB · 128K 40.7 GB
Q4_K_L
Phi 4
9.7 GB9.4 GB file
32K — · 128K —
Magistral Small 2509
15.4 GB14.8 GB file
32K 21.7 GB · 128K 41.9 GB
Q5_0
Phi 4
9.9 GB10.2 GB file
32K — · 128K —
Magistral Small 2509
not listed
Q5_K_S
Phi 4
10.8 GB10.2 GB file
32K — · 128K —
Magistral Small 2509
17.2 GB16.3 GB file
32K 23.5 GB · 128K 43.7 GB
Q5_K_L
Phi 4
11.4 GB10.9 GB file
32K — · 128K —
Magistral Small 2509
18.1 GB17.2 GB file
32K 24.4 GB · 128K 44.6 GB
BF16
Phi 4
30.0 GB~29.3 GB file
32K — · 128K —
Magistral Small 2509
48.7 GB47.2 GB file
32K 55.0 GB · 128K 75.2 GB
Phi 4
Ollama · Q4_K_M
ollama run hf.co/MaziyarPanahi/phi-4-GGUF:Q4_K_MMagistral Small 2509
Ollama · Q4_K_M
ollama run hf.co/unsloth/Magistral-Small-2509-GGUF:Q4_K_M| Spec | Phi 4 | Magistral Small 2509 |
|---|---|---|
| Publisher | Microsoft | Mistral AI |
| Parameters | 14.7B | 24.0B |
| Architecture | Phi3ForCausalLM | Mistral3ForConditionalGeneration |
| Context | 16K tokens | 128K tokens |
| Modalities | Chat, Math, Code | Chat |
| License | MIT | Apache 2.0 |
| Released | Dec 2024 | Sep 2025 |
Frequently Asked Questions
Which is better, Phi 4 or Magistral Small 2509?
Phi 4 and Magistral Small 2509 match in llmrun Score, with values of 83.8 versus 85.5; both fit 24 GB at Q4_K_M; Phi 4 is 1.6× faster on RTX 4090 (~69 vs ~43 tok/s). Choose Phi 4 for fits a 12 GB GPU and 1.6× faster on RTX 4090; choose Magistral Small 2509 for longer context window and newer release.
Which needs less VRAM, Phi 4 or Magistral Small 2509?
At Q4_K_M, Phi 4 requires 9.5 GB while Magistral Small 2509 needs 15.1 GB, making Phi 4 the easier model to run on your local setup.
Which is faster on RTX 4090?
Estimated decode speed on RTX 4090 is about 69 tok/s for Phi 4 (Q4_K_M) and 43 tok/s for Magistral Small 2509 (Q4_K_M), so Phi 4 is faster. Estimates, ±20%.
Can I run Phi 4 or Magistral Small 2509 on a 16 GB GPU?
Phi 4 fits at Q4_K_M; Magistral Small 2509 fits at Q4_K_M.
Which has a longer context window, Phi 4 or Magistral Small 2509?
Phi 4 supports 16,384 tokens and Magistral Small 2509 supports 131,072 tokens.