Phi 4 vs Qwen2.5 Coder 32B Instruct
Phi 4 leads llmrun Score 83.9 to 81.9 (ranges overlap); both fit 24 GB at Q4_K_M; Phi 4 is 2.2× faster on RTX 4090 (~69 vs ~32 tok/s).
Model B · Alibaba
Qwen2.5 Coder 32B Instruct32.8B · 32K context · Apache 2.0 · Nov 2024
Choose Phi 4 if you want…
Higher llmrun Score
83.9 vs 81.9, ranges overlap
Fits a 12 GB GPU
Q4_K_M · 12.5 GB; Qwen2.5 Coder 32B Instruct needs 13.6 GB at its smallest quant
2.2× faster on RTX 4090
~69 vs ~32 tok/s
Lighter on memory
9.5 vs 20.5 GB at Q4_K_M
Also does math
Qwen2.5 Coder 32B Instruct doesn't list it
Choose Qwen2.5 Coder 32B Instruct if you want…
Longer context window
32K vs 16K tokens
Also does function-calling
Phi 4 doesn't list it
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
Qwen2.5 Coder 32B Instruct
Doesn't fit
smallest quant needs 13.6 GB
12 GB
RTX 3060 12GB · 12 GB tier
Phi 4
Q4_K_M · ~25 tok/stight
12.5 GB · up to 8Kfits
Qwen2.5 Coder 32B Instruct
Doesn't fit
smallest quant needs 13.6 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Phi 4
Q4_K_M · ~31 tok/s
12.5 GB · up to 16Kmore headroom
Qwen2.5 Coder 32B Instruct
IQ2_M · ~25 tok/s
15.7 GB · up to 16K
24 GBreference
RTX 4090 · 24 GB tier
Phi 4
Q4_K_M · ~69 tok/s
12.5 GB · up to 16Kmore headroom
Qwen2.5 Coder 32B Instruct
Q4_K_M · ~32 tok/stight
24.3 GB · up to 8K
32 GB
RTX 5090 · 32 GB tier
Phi 4
Q4_K_M · ~122 tok/s
12.5 GB · up to 16Kfaster
Qwen2.5 Coder 32B Instruct
Q4_K_M · ~57 tok/s
24.3 GB · up to 32K
48 GB
RTX A6000 · 48 GB tier
Phi 4
Q4_K_M · ~52 tok/s
12.5 GB · up to 16Kfaster
Qwen2.5 Coder 32B Instruct
Q4_K_M · ~24 tok/s
24.3 GB · up to 32K
Mac 32 GB
Mac Mini M4 · Macs
Phi 4
Q4_K_M · ~9 tok/s
12.5 GB · up to 16Kfaster
Qwen2.5 Coder 32B Instruct
Q4_K_M · ~4 tok/s
24.3 GB · up to 16K
Mac 64 GB
Mac Studio M4 Max · Macs
Phi 4
Q4_K_M · ~40 tok/s
12.5 GB · up to 16Kfaster
Qwen2.5 Coder 32B Instruct
Q4_K_M · ~19 tok/s
24.3 GB · up to 32K
Mac 128 GB
Mac Studio M4 Max · Macs
Phi 4
Q4_K_M · ~40 tok/s
12.5 GB · up to 16Kfaster
Qwen2.5 Coder 32B Instruct
Q4_K_M · ~19 tok/s
24.3 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
Phi 4
Qwen2.5 Coder 32B Instruct
Agents
Phi 4
no data
Qwen2.5 Coder 32B Instruct
Phi 4 · #75 of 100 open models · #22 of 35 that fit 24 GB
Qwen2.5 Coder 32B Instruct · #77 of 100 open models · #23 of 35 that fit 24 GB
11 more boards (other shared and single-model boards)
Phi 4
1256.3#128/187 open
ArenaLMArena · Oct 2026
Qwen2.5 Coder 32B Instruct
1270.6#122/187 open
ArenaLMArena · Oct 2026
Only Phi 4 (6)
- GPQA Diamond56.1%
- AIME 2024/202513.8%
- MMLU-Pro70.4%
- MATH Level 564.9%
- MMLU84.8%
- BALROG11.6%
Only Qwen2.5 Coder 32B Instruct (4)
- SWE-bench Verified47.0%
- Aider Polyglot16.4%
- SWE-bench Bash Only9.0%
- GSM8K93.0%
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 —
Qwen2.5 Coder 32B Instruct
14.8 GB12.3 GB file
32K 22.8 GB · 128K —
Q3_K_S
Phi 4
7.1 GB6.5 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
15.2 GB14.4 GB file
32K 23.2 GB · 128K —
Q3_K_M
Phi 4
7.9 GB7.4 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
16.8 GB15.9 GB file
32K 24.9 GB · 128K —
Q4_0
Phi 4
8.1 GB8.4 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
17.2 GB18.6 GB file
32K 25.3 GB · 128K —
Q4_K_M
Phi 4
9.5 GB9.1 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
20.5 GB19.9 GB file
32K 28.6 GB · 128K —
Q5_K_M
Phi 4
11.2 GB10.6 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
24.2 GB23.3 GB file
32K 32.2 GB · 128K —
Q6_K
Phi 4
12.8 GB12.0 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
27.9 GB26.9 GB file
32K 35.9 GB · 128K —
Q8_0
Phi 4
15.4 GB15.6 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
33.6 GB34.8 GB file
32K 41.7 GB · 128K —
19 more quants
IQ2_XXS
Phi 4
4.8 GB4.1 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
9.9 GB9.0 GB file
32K 17.9 GB · 128K —
IQ2_XS
Phi 4
5.1 GB4.5 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
10.7 GB10.0 GB file
32K 18.7 GB · 128K —
IQ2_S
Phi 4
5.3 GB4.7 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
11.1 GB10.4 GB file
32K 19.1 GB · 128K —
IQ2_M
Phi 4
5.7 GB5.1 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
11.9 GB11.3 GB file
32K 19.9 GB · 128K —
IQ3_XXS
Phi 4
6.4 GB5.8 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
13.5 GB12.8 GB file
32K 21.6 GB · 128K —
Q2_K_S
Phi 4
6.6 GB5.2 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
not listed
IQ3_XS
Phi 4
6.8 GB6.2 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
14.4 GB13.7 GB file
32K 22.4 GB · 128K —
IQ3_S
Phi 4
7.0 GB6.5 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
14.8 GB14.4 GB file
32K 22.8 GB · 128K —
IQ3_M
Phi 4
7.3 GB6.9 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
15.6 GB14.8 GB file
32K 23.6 GB · 128K —
Q3_K_L
Phi 4
8.2 GB7.9 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
17.6 GB17.2 GB file
32K 25.7 GB · 128K —
IQ4_XS
Phi 4
8.6 GB7.9 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
18.5 GB17.7 GB file
32K 26.5 GB · 128K —
IQ4_NL
Phi 4
9.0 GB8.4 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
19.3 GB18.7 GB file
32K 27.3 GB · 128K —
Q4_1
Phi 4
9.0 GB9.3 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
not listed
Q4_K_S
Phi 4
9.0 GB8.4 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
19.3 GB18.8 GB file
32K 27.3 GB · 128K —
Q4_K_L
Phi 4
9.7 GB9.4 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
20.9 GB20.4 GB file
32K 29.0 GB · 128K —
Q5_0
Phi 4
9.9 GB10.2 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
21.3 GB22.6 GB file
32K 29.4 GB · 128K —
Q5_K_S
Phi 4
10.8 GB10.2 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
23.4 GB22.6 GB file
32K 31.4 GB · 128K —
Q5_K_L
Phi 4
11.4 GB10.9 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
24.6 GB23.7 GB file
32K 32.6 GB · 128K —
BF16
Phi 4
30.0 GB~29.3 GB file
32K — · 128K —
Qwen2.5 Coder 32B Instruct
66.4 GB~65.5 GB file
32K 74.4 GB · 128K —
Phi 4
Ollama · Q4_K_M
ollama run hf.co/MaziyarPanahi/phi-4-GGUF:Q4_K_MQwen2.5 Coder 32B Instruct
Ollama · Q4_K_M
ollama run hf.co/Qwen/Qwen2.5-Coder-32B-Instruct-GGUF:Q4_K_M| Spec | Phi 4 | Qwen2.5 Coder 32B Instruct |
|---|---|---|
| Publisher | Microsoft | Alibaba |
| Parameters | 14.7B | 32.8B |
| Architecture | Phi3ForCausalLM | Qwen2ForCausalLM |
| Context | 16K tokens | 32K tokens |
| Modalities | Chat, Math, Code | Chat, Code, Function-calling |
| License | MIT | Apache 2.0 |
| Released | Dec 2024 | Nov 2024 |
Frequently Asked Questions
Which is better, Phi 4 or Qwen2.5 Coder 32B Instruct?
Phi 4 leads llmrun Score 83.9 to 81.9 (ranges overlap); both fit 24 GB at Q4_K_M; Phi 4 is 2.2× faster on RTX 4090 (~69 vs ~32 tok/s). Choose Phi 4 for higher llmrun Score and fits a 12 GB GPU; choose Qwen2.5 Coder 32B Instruct for longer context window and also does function-calling.
Which needs less VRAM, Phi 4 or Qwen2.5 Coder 32B Instruct?
At Q4_K_M, Phi 4 requires 9.5 GB while Qwen2.5 Coder 32B Instruct needs 20.5 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 32 tok/s for Qwen2.5 Coder 32B Instruct (Q4_K_M), so Phi 4 is faster. Estimates, ±20%.
Can I run Phi 4 or Qwen2.5 Coder 32B Instruct on a 16 GB GPU?
Phi 4 fits at Q4_K_M; Qwen2.5 Coder 32B Instruct fits at IQ2_M.
Which has a longer context window, Phi 4 or Qwen2.5 Coder 32B Instruct?
Phi 4 supports 16,384 tokens and Qwen2.5 Coder 32B Instruct supports 32,768 tokens.