Back to leaderboard

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

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Not Rec.

Jul 31, 2026 · Intel Xeon® E5-4620 0

lfm2.5-thinking:1.2b

OLLAMA GGUF

lfm2 · 1.2B · Q4_K_M

Not Rec.

May 25, 2026 · Apple M4 Pro

Global Score
71 vs 60
Hardware Fit
42 vs 80
Quality Score
84 vs 52

Hardware

qwen3:30b-a3b-inst… lfm2.5-thinking:1.2b
MachineDell Inc. PowerEdge R820MacBook Pro
CPUIntel Xeon® E5-4620 0Apple M4 Pro
Cores6414
RAM256 GB48 GB
GPUMicrosoft Remote Display Adapter, Microsoft Basic Display AdapterApple M4 Pro
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348macOS 26.4.1
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3:30b-a3b-inst… lfm2.5-thinking:1.2b
Tokens/sec4.0227.0
First chunk2070 ms60 ms
TTFT2.1 s30.0 s
Load time44.5 s0.7 s
Memory usage17.7 GB2.6 GB
Memory %7%6%

HW Fit Score Breakdown

qwen3:30b-a3b-instruct-…

Speed
3/50
TTFT
9/20
Memory
30/30

lfm2.5-thinking:1.2b

Speed
50/50
TTFT
0/20
Memory
30/30

Quality

qwen3:30b-a3b-instruct-…

Reasoning
18/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

lfm2.5-thinking:1.2b

Reasoning
8/20
Coding
6/20
Instruction
10/20
Structured
7/15
Math
12/15
Multilingual
9/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Weak Math: Strong Multilingual: Strong

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