Qwen3 30B A3B vs Qwen3 30B A3B Instruct 2507
Qwen3 30B A3B Instruct 2507 leads llmrun Score 96.7 to 93.9 (ranges overlap); both fit 24 GB at Q4_K_M.
Model A · Alibaba
Qwen3 30B A3B30.5B · 3.4B active · 40K context · Apache 2.0 · Apr 2025
Model B · Alibaba
Qwen3 30B A3B Instruct 250730.5B · 3.4B active · 256K context · Apache 2.0 · Jul 2025
Choose Qwen3 30B A3B Instruct 2507 if you want…
Higher llmrun Score
96.7 vs 93.9, ranges overlap
Stronger at reasoning
92.5 vs 83.7
Longer context window
256K vs 40K tokens
Newer release
Jul 2025 vs Apr 2025
Qwen3 30B A3B: no clear edge over Qwen3 30B A3B Instruct 2507 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
Qwen3 30B A3B
Doesn't fit
smallest quant needs 9.5 GB
Qwen3 30B A3B Instruct 2507
Doesn't fit
smallest quant needs 9.5 GB
12 GB
RTX 3060 12GB · 12 GB tier
Qwen3 30B A3B
IQ2_M · ~130 tok/s
11.4 GB · up to 16K
Qwen3 30B A3B Instruct 2507
IQ2_M · ~130 tok/s
11.4 GB · up to 16K
16 GB
RTX 5060 Ti 16GB · 16 GB tier
Qwen3 30B A3B
Q3_K_M · ~119 tok/s
16 GB · up to 16K
Qwen3 30B A3B Instruct 2507
Q3_K_M · ~119 tok/s
16 GB · up to 16K
24 GBreference
RTX 4090 · 24 GB tier
Qwen3 30B A3B
Q4_K_M · ~173 tok/s
19.4 GB · up to 40K
Qwen3 30B A3B Instruct 2507
Q4_K_M · ~173 tok/s
19.4 GB · up to 64K
32 GB
RTX 5090 · 32 GB tier
Qwen3 30B A3B
Q4_K_M · ~227 tok/s
19.4 GB · up to 40K
Qwen3 30B A3B Instruct 2507
Q4_K_M · ~227 tok/s
19.4 GB · up to 256K
48 GB
RTX A6000 · 48 GB tier
Qwen3 30B A3B
Q4_K_M · ~148 tok/s
19.4 GB · up to 40K
Qwen3 30B A3B Instruct 2507
Q4_K_M · ~148 tok/s
19.4 GB · up to 256K
Mac 32 GB
Mac Mini M4 · Macs
Qwen3 30B A3B
Q4_K_M · ~29 tok/s
19.4 GB · up to 40K
Qwen3 30B A3B Instruct 2507
Q4_K_M · ~29 tok/s
19.4 GB · up to 128K
Mac 64 GB
Mac Studio M4 Max · Macs
Qwen3 30B A3B
Q4_K_M · ~67 tok/s
19.4 GB · up to 40K
Qwen3 30B A3B Instruct 2507
Q4_K_M · ~67 tok/s
19.4 GB · up to 256K
Mac 128 GB
Mac Studio M4 Max · Macs
Qwen3 30B A3B
Q4_K_M · ~67 tok/s
19.4 GB · up to 40K
Qwen3 30B A3B Instruct 2507
Q4_K_M · ~67 tok/s
19.4 GB · up to 256K
Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).
Overall
Qwen3 30B A3B
Qwen3 30B A3B Instruct 2507
Reasoning
Qwen3 30B A3B
Qwen3 30B A3B Instruct 2507
Qwen3 30B A3B · #68 of 100 open models · #17 of 35 that fit 24 GB
Qwen3 30B A3B Instruct 2507 · #60 of 100 open models · #14 of 35 that fit 24 GB
Benchmarks
4 shared boards: Qwen3 30B A3B leads 2, Qwen3 30B A3B Instruct 2507 leads 2 · Benchmarks imported Oct 2026
Qwen3 30B A3B
61.7%#41/98 open
IndependentEpoch AI · Apr 2025
Qwen3 30B A3B Instruct 2507
55.6%#49/98 open
IndependentEpoch AI · Jul 2025
Qwen3 30B A3B
62.8%#35/86 open
IndependentEpoch AI · Apr 2025
Qwen3 30B A3B Instruct 2507
62.2%#36/86 open
IndependentEpoch AI · Jul 2025
Qwen3 30B A3B
60.3%#47/68 open
Lab-reportedEpoch AI · Apr 2025
Qwen3 30B A3B Instruct 2507
67.2%#36/68 open
Lab-reportedEpoch AI · Jul 2025
Qwen3 30B A3B
15.8%#40/54 open
Lab-reportedEpoch AI · Apr 2025
Qwen3 30B A3B Instruct 2507
22.4%#31/54 open
Lab-reportedEpoch AI · Jul 2025
3 more boards (other shared and single-model boards)
Qwen3 30B A3B
1326.7#90/187 open
ArenaLMArena · Oct 2026
Qwen3 30B A3B Instruct 2507
1382.3#60/187 open
ArenaLMArena · Oct 2026
Only Qwen3 30B A3B (2)
- WeirdML29.8%
- Fiction.LiveBench40.6%
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
Qwen3 30B A3B
13.4 GB11.3 GB file
32K 14.9 GB · 128K —
Qwen3 30B A3B Instruct 2507
13.4 GB11.3 GB file
32K 14.9 GB · 128K 19.7 GB
Q3_K_S
Qwen3 30B A3B
13.8 GB13.3 GB file
32K 15.3 GB · 128K —
Qwen3 30B A3B Instruct 2507
13.8 GB13.3 GB file
32K 15.3 GB · 128K 20.1 GB
Q3_K_M
Qwen3 30B A3B
15.3 GB14.7 GB file
32K 16.8 GB · 128K —
Qwen3 30B A3B Instruct 2507
15.3 GB14.7 GB file
32K 16.8 GB · 128K 21.6 GB
Q4_0
Qwen3 30B A3B
15.7 GB17.4 GB file
32K 17.2 GB · 128K —
Qwen3 30B A3B Instruct 2507
15.7 GB17.4 GB file
32K 17.2 GB · 128K 22.0 GB
Q4_K_M
Qwen3 30B A3B
18.7 GB18.6 GB file
32K 20.2 GB · 128K —
Qwen3 30B A3B Instruct 2507
18.7 GB18.6 GB file
32K 20.2 GB · 128K 25.1 GB
Q5_K_M
Qwen3 30B A3B
22.2 GB21.7 GB file
32K 23.7 GB · 128K —
Qwen3 30B A3B Instruct 2507
22.2 GB21.7 GB file
32K 23.7 GB · 128K 28.5 GB
Q6_K
Qwen3 30B A3B
25.6 GB25.1 GB file
32K 27.1 GB · 128K —
Qwen3 30B A3B Instruct 2507
25.6 GB25.1 GB file
32K 27.1 GB · 128K 31.9 GB
Q8_0
Qwen3 30B A3B
30.9 GB32.5 GB file
32K 32.4 GB · 128K —
Qwen3 30B A3B Instruct 2507
30.9 GB32.5 GB file
32K 32.4 GB · 128K 37.3 GB
19 more quants
IQ2_XXS
Qwen3 30B A3B
8.8 GB10.4 GB file
32K 10.3 GB · 128K —
Qwen3 30B A3B Instruct 2507
8.8 GB10.3 GB file
32K 10.3 GB · 128K 15.1 GB
IQ2_XS
Qwen3 30B A3B
9.6 GB9.1 GB file
32K 11.1 GB · 128K —
Qwen3 30B A3B Instruct 2507
9.6 GB8.7 GB file
32K 11.1 GB · 128K 15.9 GB
IQ2_S
Qwen3 30B A3B
9.9 GB9.2 GB file
32K 11.5 GB · 128K —
Qwen3 30B A3B Instruct 2507
9.9 GB8.7 GB file
32K 11.5 GB · 128K 16.3 GB
IQ2_M
Qwen3 30B A3B
10.7 GB10.9 GB file
32K 12.2 GB · 128K —
Qwen3 30B A3B Instruct 2507
10.7 GB10.8 GB file
32K 12.2 GB · 128K 17.1 GB
IQ3_XXS
Qwen3 30B A3B
12.2 GB12.9 GB file
32K 13.7 GB · 128K —
Qwen3 30B A3B Instruct 2507
12.2 GB12.9 GB file
32K 13.7 GB · 128K 18.6 GB
Q2_K_S
Qwen3 30B A3B
not listed
Qwen3 30B A3B Instruct 2507
12.6 GB10.5 GB file
32K 14.1 GB · 128K 19.0 GB
IQ3_XS
Qwen3 30B A3B
13.0 GB12.7 GB file
32K 14.5 GB · 128K —
Qwen3 30B A3B Instruct 2507
13.0 GB12.7 GB file
32K 14.5 GB · 128K 19.3 GB
IQ3_S
Qwen3 30B A3B
13.4 GB14.0 GB file
32K 14.9 GB · 128K —
Qwen3 30B A3B Instruct 2507
13.4 GB10.3 GB file
32K 14.9 GB · 128K 19.7 GB
IQ3_M
Qwen3 30B A3B
14.1 GB14.1 GB file
32K 15.7 GB · 128K —
Qwen3 30B A3B Instruct 2507
14.1 GB14.1 GB file
32K 15.7 GB · 128K 20.5 GB
Q3_K_L
Qwen3 30B A3B
16.1 GB15.9 GB file
32K 17.6 GB · 128K —
Qwen3 30B A3B Instruct 2507
16.1 GB15.9 GB file
32K 17.6 GB · 128K 22.4 GB
IQ4_XS
Qwen3 30B A3B
16.8 GB16.4 GB file
32K 18.3 GB · 128K —
Qwen3 30B A3B Instruct 2507
16.8 GB16.4 GB file
32K 18.3 GB · 128K 23.2 GB
IQ4_NL
Qwen3 30B A3B
17.6 GB17.3 GB file
32K 19.1 GB · 128K —
Qwen3 30B A3B Instruct 2507
17.6 GB17.3 GB file
32K 19.1 GB · 128K 23.9 GB
Q4_1
Qwen3 30B A3B
17.6 GB19.2 GB file
32K 19.1 GB · 128K —
Qwen3 30B A3B Instruct 2507
17.6 GB19.2 GB file
32K 19.1 GB · 128K 23.9 GB
Q4_K_S
Qwen3 30B A3B
17.6 GB17.5 GB file
32K 19.1 GB · 128K —
Qwen3 30B A3B Instruct 2507
17.6 GB17.5 GB file
32K 19.1 GB · 128K 23.9 GB
Q4_K_L
Qwen3 30B A3B
19.1 GB18.9 GB file
32K 20.6 GB · 128K —
Qwen3 30B A3B Instruct 2507
19.1 GB18.9 GB file
32K 20.6 GB · 128K 25.4 GB
Q5_0
Qwen3 30B A3B
19.5 GB21.1 GB file
32K 21.0 GB · 128K —
Qwen3 30B A3B Instruct 2507
19.5 GB21.1 GB file
32K 21.0 GB · 128K 25.8 GB
Q5_K_S
Qwen3 30B A3B
21.4 GB21.1 GB file
32K 22.9 GB · 128K —
Qwen3 30B A3B Instruct 2507
21.4 GB21.1 GB file
32K 22.9 GB · 128K 27.7 GB
Q5_K_L
Qwen3 30B A3B
22.5 GB21.9 GB file
32K 24.1 GB · 128K —
Qwen3 30B A3B Instruct 2507
22.5 GB21.9 GB file
32K 24.1 GB · 128K 28.9 GB
BF16
Qwen3 30B A3B
61.5 GB61.1 GB file
32K 63.0 GB · 128K —
Qwen3 30B A3B Instruct 2507
61.5 GB61.1 GB file
32K 63.0 GB · 128K 67.8 GB
Qwen3 30B A3B
Ollama · Q4_K_M
ollama run hf.co/MaziyarPanahi/Qwen3-30B-A3B-GGUF:Q4_K_MQwen3 30B A3B Instruct 2507
Ollama · Q4_K_M
ollama run hf.co/unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF:Q4_K_M| Spec | Qwen3 30B A3B | Qwen3 30B A3B Instruct 2507 |
|---|---|---|
| Publisher | Alibaba | Alibaba |
| Parameters | 30.5B | 30.5B |
| Active parameters | 3.4B per token | 3.4B per token |
| Architecture | Qwen3MoeForCausalLM | Qwen3MoeForCausalLM |
| Context | 40K tokens | 256K tokens |
| Modalities | Chat, Function-calling | Chat, Function-calling |
| License | Apache 2.0 | Apache 2.0 |
| Released | Apr 2025 | Jul 2025 |
Frequently Asked Questions
Which is better, Qwen3 30B A3B or Qwen3 30B A3B Instruct 2507?
Qwen3 30B A3B Instruct 2507 leads llmrun Score 96.7 to 93.9 (ranges overlap); both fit 24 GB at Q4_K_M. Choose Qwen3 30B A3B Instruct 2507 for higher llmrun Score and stronger at reasoning.
Which needs less VRAM, Qwen3 30B A3B or Qwen3 30B A3B Instruct 2507?
At Q4_K_M, Qwen3 30B A3B requires 18.7 GB while Qwen3 30B A3B Instruct 2507 needs 18.7 GB, making Qwen3 30B A3B the easier model to run on your local setup.
Which is faster on RTX 4090?
Estimated decode speed on RTX 4090 is about 173 tok/s for Qwen3 30B A3B (Q4_K_M) and 173 tok/s for Qwen3 30B A3B Instruct 2507 (Q4_K_M), so Qwen3 30B A3B is faster. Estimates, ±20%.
Can I run Qwen3 30B A3B or Qwen3 30B A3B Instruct 2507 on a 16 GB GPU?
Qwen3 30B A3B fits at Q3_K_M; Qwen3 30B A3B Instruct 2507 fits at Q3_K_M.
Which has a longer context window, Qwen3 30B A3B or Qwen3 30B A3B Instruct 2507?
Qwen3 30B A3B supports 40,960 tokens and Qwen3 30B A3B Instruct 2507 supports 262,144 tokens.