Back to leaderboard

lmstudio-community/gemma-4-e4b-it

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

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

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Excellent

Mar 5, 2026 · Apple M1 Max

Global Score
76 vs 85
Hardware Fit
67 vs 95
Quality Score
80 vs 80

Hardware

lmstudio-community… 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

lmstudio-community… qwen3.5:9b
Tokens/sec10.823.1
First chunk44 ms358 ms
TTFT2.0 s358 ms
Load time10.9 s3.6 s
Memory usage0.0 GB9.1 GB
Memory %0%28%

HW Fit Score Breakdown

lmstudio-community/gemm…

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

qwen3.5:9b

Speed
45/50
TTFT
20/20
Memory
30/30

Quality

lmstudio-community/gemm…

Reasoning
14/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

qwen3.5:9b

Reasoning
14/20
Coding
16/20
Instruction
15/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View lmstudio-community… 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