Back to leaderboard

hf.co/unsloth/gemma-4-E4B-it-GGUF:Q5_K_M

OLLAMA GGUF

gemma4 · 7.52B · unknown

Excellent

Aug 23, 2026 · Apple M1 Pro

neural-chat:7b

OLLAMA GGUF

llama · 7B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score
88 vs 67
Hardware Fit
100 vs 96
Quality Score
83 vs 55

Hardware

hf.co/unsloth/gemm… neural-chat:7b
MachineMacBook ProMacBook Air
CPUApple M1 ProApple M4
Cores1010
RAM16 GB32 GB
GPUApple M1 ProApple M4
OSmacOS 26.6.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

hf.co/unsloth/gemm… neural-chat:7b
Tokens/sec28.322.5
First chunk224 msN/A
TTFT224 ms242 ms
Load time4.5 s0.4 s
Memory usage3.6 GB4.5 GB
Memory %23%14%

HW Fit Score Breakdown

hf.co/unsloth/gemma-4-E…

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

neural-chat:7b

Speed
36/50
TTFT
30/20
Memory
30/30

Quality

hf.co/unsloth/gemma-4-E…

Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

neural-chat:7b

Reasoning
7/20
Coding
9/20
Instruction
12/20
Structured
12/15
Math
7/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View hf.co/unsloth/gemm… details | View neural-chat:7b 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