Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M4

lfm2-24b-a2b

LM-STUDIO GGUF
Not Rec.

Mar 6, 2026 · Apple M4 Pro

Global Score
48 vs 18
Hardware Fit
77 vs 59
Quality Score
35 vs 0

Hardware

qwen3.5:4b lfm2-24b-a2b
MachineMac miniMac mini
CPUApple M4Apple M4 Pro
Cores1014
RAM16 GB64 GB
GPUApple M4Apple M4 Pro
OSmacOS 26.3macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:4b lfm2-24b-a2b
Tokens/sec18.96.6
First chunk316 ms1025 ms
TTFT13.0 s1.0 s
Load time3.7 sN/A
Memory usage5.9 GB0.0 GB
Memory %37%0%

HW Fit Score Breakdown

qwen3.5:4b

Speed
43/50
TTFT
4/20
Memory
30/30

lfm2-24b-a2b

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

Quality

qwen3.5:4b

Reasoning
10/20
Coding
1/20
Instruction
4/20
Structured
3/15
Math
8/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Adequate Multilingual: Strong

lfm2-24b-a2b

Reasoning
0/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
View qwen3.5:4b details | View lfm2-24b-a2b 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