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

mistral:latest

OLLAMA GGUF

llama · 7.2B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

Global Score
88 vs 73
Hardware Fit
100 vs 96
Quality Score
83 vs 63

Hardware

hf.co/unsloth/gemm… mistral:latest
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… mistral:latest
Tokens/sec28.322.5
First chunk224 msN/A
TTFT224 ms257 ms
Load time4.5 s0.6 s
Memory usage3.6 GB10.1 GB
Memory %23%32%

HW Fit Score Breakdown

hf.co/unsloth/gemma-4-E…

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

mistral:latest

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

mistral:latest

Reasoning
8/20
Coding
12/20
Instruction
15/20
Structured
14/15
Math
5/15
Multilingual
9/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View hf.co/unsloth/gemm… details | View mistral:latest 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