Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Excellent

Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S

liquid/lfm2-24b-a2b

LM-STUDIO MLX

lfm2_moe · 24B · 4bit

Good

Mar 19, 2026 · Apple M4

Global Score
82 vs 74
Hardware Fit
81 vs 84
Quality Score
82 vs 69

Hardware

qwen3.5:9b liquid/lfm2-24b-a2b
MachineAZW GTR ProMac mini
CPUAMD RYZEN AI MAX+ 395 w/ Radeon 8060SApple M4
Cores3210
RAM125 GB24 GB
GPUIntegrated / Apple SiliconApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced

Performance

qwen3.5:9b liquid/lfm2-24b-a2b
Tokens/sec30.858.9
First chunk195 ms28 ms
TTFT195 ms481 ms
Load time6.8 sN/A
Memory usage18.8 GB17.5 GB
Memory %15%73%

HW Fit Score Breakdown

qwen3.5:9b

Speed
31/50
TTFT
20/20
Memory
30/30

liquid/lfm2-24b-a2b

Speed
50/50
TTFT
20/20
Memory
14/30

Quality

qwen3.5:9b

Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

liquid/lfm2-24b-a2b

Reasoning
11/20
Coding
12/20
Instruction
16/20
Structured
13/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:9b details | View liquid/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