Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

lfm2-24b-a2b

LM-STUDIO GGUF
Not Rec.

Mar 6, 2026 · Apple M4 Pro

Global Score
57 vs 18
Hardware Fit
61 vs 59
Quality Score
55 vs 0

Hardware

qwen3.5:9b lfm2-24b-a2b
MachineAZW GTR ProMac mini
CPUAMD RYZEN AI MAX+ 395Apple M4 Pro
Cores3214
RAM125 GB64 GB
GPUAMD Radeon 8060SApple M4 Pro
OSUbuntu 24.04.4 LTSmacOS 15.7.4
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen3.5:9b lfm2-24b-a2b
Tokens/sec30.36.6
First chunk205 ms1025 ms
TTFT8.7 s1.0 s
Load time5.6 sN/A
Memory usage18.8 GB0.0 GB
Memory %15%0%

HW Fit Score Breakdown

qwen3.5:9b

Speed
30/50
TTFT
1/20
Memory
30/30

lfm2-24b-a2b

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

Quality

qwen3.5:9b

Reasoning
17/20
Coding
2/20
Instruction
7/20
Structured
8/15
Math
12/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong 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 qwen3.5:9b 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