Back to leaderboard

unsloth/qwen3.5-9b@q4_k_m

LM-STUDIO GGUF

qwen35 · 9B · Q4_K_M

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

mlx-community/Llama-3.2-1B-Instruct-4bit

LM-STUDIO GGUF
Marginal

Mar 5, 2026 · Apple M4

Global Score
73 vs 57
Hardware Fit
52 vs 100
Quality Score
82 vs 39

Hardware

unsloth/qwen3.5-9b… mlx-community/Llam…
MachineDocker ContainerMacBook Air
CPUIntel Gen Intel® Core™ i9-11900HApple M4
Cores1610
RAM15 GB32 GB
GPUTigerLake-H GT1 [UHD Graphics]Apple M4
OSUbuntu 26.04 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced

Performance

unsloth/qwen3.5-9b… mlx-community/Llam…
Tokens/sec6.5126.4
First chunk13 ms139 ms
TTFT4.1 s139 ms
Load time10.8 sN/A
Memory usage2.2 GB0.3 GB
Memory %14%1%

HW Fit Score Breakdown

unsloth/qwen3.5-9b@q4_k_m

Speed
11/50
TTFT
11/20
Memory
30/30

mlx-community/Llama-3.2…

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

Quality

unsloth/qwen3.5-9b@q4_k_m

Reasoning
15/20
Coding
17/20
Instruction
16/20
Structured
15/15
Math
9/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

mlx-community/Llama-3.2…

Reasoning
5/20
Coding
3/20
Instruction
15/20
Structured
10/15
Math
1/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Strong Structured Output: Adequate Math: Poor Multilingual: Adequate
View unsloth/qwen3.5-9b… details | View mlx-community/Llam… 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