Qwen2.5 32B Instruct vs Qwen2.5 Coder 32B Instruct
Qwen2.5 32B Instruct and Qwen2.5 Coder 32B Instruct match in llmrun Score, with values of 80.4 versus 81.9; both fit 24 GB at Q4_K_M.
Model A · Alibaba
Qwen2.5 32B Instruct32.8B · 32K context · Apache 2.0 · Sep 2024
Model B · Alibaba
Qwen2.5 Coder 32B Instruct32.8B · 32K context · Apache 2.0 · Nov 2024
Choose Qwen2.5 Coder 32B Instruct if you want…
Also does code
Qwen2.5 32B Instruct doesn't list it
Qwen2.5 32B Instruct: no clear edge over Qwen2.5 Coder 32B Instruct 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
Qwen2.5 32B Instruct
Doesn't fit
smallest quant needs 13.6 GB
Qwen2.5 Coder 32B Instruct
Doesn't fit
smallest quant needs 13.6 GB
12 GB
RTX 3060 12GB · 12 GB tier
Qwen2.5 32B Instruct
Doesn't fit
smallest quant needs 13.6 GB
Qwen2.5 Coder 32B Instruct
Doesn't fit
smallest quant needs 13.6 GB
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Qwen2.5 32B Instruct
IQ2_M · ~25 tok/s
15.7 GB · up to 16K
Qwen2.5 Coder 32B Instruct
IQ2_M · ~25 tok/s
15.7 GB · up to 16K
24 GBreference
RTX 4090 · 24 GB tier
Qwen2.5 32B Instruct
Q4_K_M · ~32 tok/stight
24.3 GB · up to 8K
Qwen2.5 Coder 32B Instruct
Q4_K_M · ~32 tok/stight
24.3 GB · up to 8K
32 GB
RTX 5090 · 32 GB tier
Qwen2.5 32B Instruct
Q4_K_M · ~57 tok/s
24.3 GB · up to 32K
Qwen2.5 Coder 32B Instruct
Q4_K_M · ~57 tok/s
24.3 GB · up to 32K
48 GB
RTX A6000 · 48 GB tier
Qwen2.5 32B Instruct
Q4_K_M · ~24 tok/s
24.3 GB · up to 32K
Qwen2.5 Coder 32B Instruct
Q4_K_M · ~24 tok/s
24.3 GB · up to 32K
Mac 32 GB
Mac Mini M4 · Macs
Qwen2.5 32B Instruct
Q4_K_M · ~4 tok/s
24.3 GB · up to 16K
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
Qwen2.5 32B Instruct
Q4_K_M · ~19 tok/s
24.3 GB · up to 32K
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
Qwen2.5 32B Instruct
Q4_K_M · ~19 tok/s
24.3 GB · up to 32K
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
Qwen2.5 32B Instruct
Qwen2.5 Coder 32B Instruct
Agents
Qwen2.5 32B Instruct
no data
Qwen2.5 Coder 32B Instruct
Qwen2.5 32B Instruct · #82 of 100 open models · #24 of 35 that fit 24 GB
Qwen2.5 Coder 32B Instruct · #77 of 100 open models · #23 of 35 that fit 24 GB
9 more boards (other shared and single-model boards)
Only Qwen2.5 32B Instruct (4)
- GPQA Diamond46.1%
- AIME 2024/20257.4%
- MMLU-Pro69.2%
- MATH Level 556.1%
Only Qwen2.5 Coder 32B Instruct (5)
- SWE-bench Verified47.0%
- LMArena Text1270.6
- 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
Qwen2.5 32B Instruct
14.8 GB12.3 GB file
32K 22.8 GB · 128K —
Qwen2.5 Coder 32B Instruct
14.8 GB12.3 GB file
32K 22.8 GB · 128K —
Q3_K_S
Qwen2.5 32B Instruct
15.2 GB14.4 GB file
32K 23.2 GB · 128K —
Qwen2.5 Coder 32B Instruct
15.2 GB14.4 GB file
32K 23.2 GB · 128K —
Q3_K_M
Qwen2.5 32B Instruct
16.8 GB15.9 GB file
32K 24.9 GB · 128K —
Qwen2.5 Coder 32B Instruct
16.8 GB15.9 GB file
32K 24.9 GB · 128K —
Q4_0
Qwen2.5 32B Instruct
17.2 GB18.6 GB file
32K 25.3 GB · 128K —
Qwen2.5 Coder 32B Instruct
17.2 GB18.6 GB file
32K 25.3 GB · 128K —
Q4_K_M
Qwen2.5 32B Instruct
20.5 GB19.9 GB file
32K 28.6 GB · 128K —
Qwen2.5 Coder 32B Instruct
20.5 GB19.9 GB file
32K 28.6 GB · 128K —
Q5_K_M
Qwen2.5 32B Instruct
24.2 GB23.3 GB file
32K 32.2 GB · 128K —
Qwen2.5 Coder 32B Instruct
24.2 GB23.3 GB file
32K 32.2 GB · 128K —
Q6_K
Qwen2.5 32B Instruct
27.9 GB26.9 GB file
32K 35.9 GB · 128K —
Qwen2.5 Coder 32B Instruct
27.9 GB26.9 GB file
32K 35.9 GB · 128K —
Q8_0
Qwen2.5 32B Instruct
33.6 GB34.8 GB file
32K 41.7 GB · 128K —
Qwen2.5 Coder 32B Instruct
33.6 GB34.8 GB file
32K 41.7 GB · 128K —
19 more quants
IQ2_XXS
Qwen2.5 32B Instruct
9.9 GB9.0 GB file
32K 17.9 GB · 128K —
Qwen2.5 Coder 32B Instruct
9.9 GB9.0 GB file
32K 17.9 GB · 128K —
IQ2_XS
Qwen2.5 32B Instruct
10.7 GB10.0 GB file
32K 18.7 GB · 128K —
Qwen2.5 Coder 32B Instruct
10.7 GB10.0 GB file
32K 18.7 GB · 128K —
IQ2_S
Qwen2.5 32B Instruct
11.1 GB10.4 GB file
32K 19.1 GB · 128K —
Qwen2.5 Coder 32B Instruct
11.1 GB10.4 GB file
32K 19.1 GB · 128K —
IQ2_M
Qwen2.5 32B Instruct
11.9 GB11.3 GB file
32K 19.9 GB · 128K —
Qwen2.5 Coder 32B Instruct
11.9 GB11.3 GB file
32K 19.9 GB · 128K —
IQ3_XXS
Qwen2.5 32B Instruct
13.5 GB12.8 GB file
32K 21.6 GB · 128K —
Qwen2.5 Coder 32B Instruct
13.5 GB12.8 GB file
32K 21.6 GB · 128K —
Q2_K_S
Qwen2.5 32B Instruct
13.9 GB11.5 GB file
32K 22.0 GB · 128K —
Qwen2.5 Coder 32B Instruct
not listed
IQ3_XS
Qwen2.5 32B Instruct
14.4 GB13.7 GB file
32K 22.4 GB · 128K —
Qwen2.5 Coder 32B Instruct
14.4 GB13.7 GB file
32K 22.4 GB · 128K —
IQ3_S
Qwen2.5 32B Instruct
14.8 GB14.4 GB file
32K 22.8 GB · 128K —
Qwen2.5 Coder 32B Instruct
14.8 GB14.4 GB file
32K 22.8 GB · 128K —
IQ3_M
Qwen2.5 32B Instruct
15.6 GB14.8 GB file
32K 23.6 GB · 128K —
Qwen2.5 Coder 32B Instruct
15.6 GB14.8 GB file
32K 23.6 GB · 128K —
Q3_K_L
Qwen2.5 32B Instruct
17.6 GB17.2 GB file
32K 25.7 GB · 128K —
Qwen2.5 Coder 32B Instruct
17.6 GB17.2 GB file
32K 25.7 GB · 128K —
IQ4_XS
Qwen2.5 32B Instruct
18.5 GB17.7 GB file
32K 26.5 GB · 128K —
Qwen2.5 Coder 32B Instruct
18.5 GB17.7 GB file
32K 26.5 GB · 128K —
IQ4_NL
Qwen2.5 32B Instruct
not listed
Qwen2.5 Coder 32B Instruct
19.3 GB18.7 GB file
32K 27.3 GB · 128K —
Q4_1
Qwen2.5 32B Instruct
19.3 GB20.6 GB file
32K 27.3 GB · 128K —
Qwen2.5 Coder 32B Instruct
not listed
Q4_K_S
Qwen2.5 32B Instruct
19.3 GB18.8 GB file
32K 27.3 GB · 128K —
Qwen2.5 Coder 32B Instruct
19.3 GB18.8 GB file
32K 27.3 GB · 128K —
Q4_K_L
Qwen2.5 32B Instruct
20.9 GB20.4 GB file
32K 29.0 GB · 128K —
Qwen2.5 Coder 32B Instruct
20.9 GB20.4 GB file
32K 29.0 GB · 128K —
Q5_0
Qwen2.5 32B Instruct
21.3 GB22.6 GB file
32K 29.4 GB · 128K —
Qwen2.5 Coder 32B Instruct
21.3 GB22.6 GB file
32K 29.4 GB · 128K —
Q5_K_S
Qwen2.5 32B Instruct
23.4 GB22.6 GB file
32K 31.4 GB · 128K —
Qwen2.5 Coder 32B Instruct
23.4 GB22.6 GB file
32K 31.4 GB · 128K —
Q5_K_L
Qwen2.5 32B Instruct
24.6 GB23.7 GB file
32K 32.6 GB · 128K —
Qwen2.5 Coder 32B Instruct
24.6 GB23.7 GB file
32K 32.6 GB · 128K —
BF16
Qwen2.5 32B Instruct
66.4 GB~65.5 GB file
32K 74.4 GB · 128K —
Qwen2.5 Coder 32B Instruct
66.4 GB~65.5 GB file
32K 74.4 GB · 128K —
Qwen2.5 32B Instruct
Ollama · Q4_K_M
ollama run hf.co/bartowski/Qwen2.5-32B-Instruct-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 | Qwen2.5 32B Instruct | Qwen2.5 Coder 32B Instruct |
|---|---|---|
| Publisher | Alibaba | Alibaba |
| Parameters | 32.8B | 32.8B |
| Architecture | Qwen2ForCausalLM | Qwen2ForCausalLM |
| Context | 32K tokens | 32K tokens |
| Modalities | Chat, Function-calling | Chat, Code, Function-calling |
| License | Apache 2.0 | Apache 2.0 |
| Released | Sep 2024 | Nov 2024 |
Frequently Asked Questions
Which is better, Qwen2.5 32B Instruct or Qwen2.5 Coder 32B Instruct?
Qwen2.5 32B Instruct and Qwen2.5 Coder 32B Instruct match in llmrun Score, with values of 80.4 versus 81.9; both fit 24 GB at Q4_K_M. Choose Qwen2.5 Coder 32B Instruct for also does code.
Which needs less VRAM, Qwen2.5 32B Instruct or Qwen2.5 Coder 32B Instruct?
At Q4_K_M, Qwen2.5 32B Instruct requires 20.5 GB while Qwen2.5 Coder 32B Instruct needs 20.5 GB, making Qwen2.5 32B Instruct the easier model to run on your local setup.
Which is faster on RTX 4090?
Estimated decode speed on RTX 4090 is about 32 tok/s for Qwen2.5 32B Instruct (Q4_K_M) and 32 tok/s for Qwen2.5 Coder 32B Instruct (Q4_K_M), so Qwen2.5 32B Instruct is faster. Estimates, ±20%.
Can I run Qwen2.5 32B Instruct or Qwen2.5 Coder 32B Instruct on a 16 GB GPU?
Qwen2.5 32B Instruct fits at IQ2_M; Qwen2.5 Coder 32B Instruct fits at IQ2_M.
Which has a longer context window, Qwen2.5 32B Instruct or Qwen2.5 Coder 32B Instruct?
Qwen2.5 32B Instruct supports 32,768 tokens and Qwen2.5 Coder 32B Instruct supports 32,768 tokens.