Back to leaderboard

gemma-4-e4b-it@q5_k_xl

LM-STUDIO GGUF

gemma4 · Q5_K_XL

Good

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

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M1 Max

Global Score
77 vs 53
Hardware Fit
59 vs 72
Quality Score
84 vs 45

Hardware

gemma-4-e4b-it@q5_… qwen3.5:9b
MachineDocker ContainerMacBook Pro
CPUIntel Gen Intel® Core™ i9-11900HApple M1 Max
Cores1610
RAM15 GB32 GB
GPUTigerLake-H GT1 [UHD Graphics]Apple M1 Max
OSUbuntu 26.04 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced

Performance

gemma-4-e4b-it@q5_… qwen3.5:9b
Tokens/sec9.318.6
First chunk51 ms403 ms
TTFT3.4 s10.2 s
Load time12.2 s4.3 s
Memory usage0.0 GB9.1 GB
Memory %0%28%

HW Fit Score Breakdown

gemma-4-e4b-it@q5_k_xl

Speed
17/50
TTFT
12/20
Memory
30/30

qwen3.5:9b

Speed
38/50
TTFT
4/20
Memory
30/30

Quality

gemma-4-e4b-it@q5_k_xl

Reasoning
15/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
9/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

qwen3.5:9b

Reasoning
12/20
Coding
3/20
Instruction
5/20
Structured
6/15
Math
11/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong
View gemma-4-e4b-it@q5_… details | View qwen3.5:9b 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