Back to leaderboard

qwen3:30b-a3b-instruct-2507-q4_K_M

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Jul 31, 2026 · Intel Core™ i9-14900K

qwen3:0.6b

OLLAMA GGUF

qwen3 · 751.63M · Q4_K_M

Good

Apr 29, 2026 · Intel Core™ i5-8350U

Global Score
83 vs 61
Hardware Fit
70 vs 85
Quality Score
89 vs 51

Hardware

qwen3:30b-a3b-inst… qwen3:0.6b
MachineMicro-Star International Co., Ltd. MS-7D98LENOVO 20L7CTO1WW
CPUIntel Core™ i9-14900KIntel Core™ i5-8350U
Cores328
RAM128 GB23 GB
GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000Kaby Lake-R GT2 [UHD Graphics 620]
OSMicrosoft Windows 11 Pro 10.0.26200Fedora Linux 43
Archx64x64
Power Modebalancedlow-power

Performance

qwen3:30b-a3b-inst… qwen3:0.6b
Tokens/sec21.027.0
First chunk473 ms597 ms
TTFT473 ms8.7 s
Load time8.6 s1.8 s
Memory usage17.7 GB0.9 GB
Memory %14%4%

HW Fit Score Breakdown

qwen3:30b-a3b-instruct-…

Speed
20/50
TTFT
20/20
Memory
30/30

qwen3:0.6b

Speed
50/50
TTFT
5/20
Memory
30/30

Quality

qwen3:30b-a3b-instruct-…

Reasoning
17/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3:0.6b

Reasoning
14/20
Coding
0/20
Instruction
9/20
Structured
12/15
Math
9/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Adequate
View qwen3:30b-a3b-inst… details | View qwen3:0.6b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest