lmstudio-community/gemma-4-e4b-it
LM-STUDIO GGUFgemma4 · Q4_K_M
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
qwen3.5:0.8b
OLLAMA GGUFqwen35 · 873.44M · Q8_0
Mar 5, 2026 · Apple M1 Max
Global Score
76 vs 62
Hardware Fit
67 vs 100
Quality Score
80 vs 46
Hardware
lmstudio-community… qwen3.5:0.8b
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… qwen3.5:0.8b
Tokens/sec10.867.6
First chunk44 ms209 ms
TTFT2.0 s209 ms
Load time10.9 s1.9 s
Memory usage0.0 GB2.6 GB
Memory %0%8%
HW Fit Score Breakdown
lmstudio-community/gemm…
Speed
20/50
TTFT
17/20
Memory
30/30
qwen3.5:0.8b
Speed
50/50
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
qwen3.5:0.8b
Reasoning
9/20
Coding
4/20
Instruction
11/20
Structured
13/15
Math
3/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest