qwen3.5:latest
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 8, 2026 · Apple M4
hf.co/unsloth/gemma-4-E4B-it-GGUF:Q4_K_M
OLLAMA GGUFgemma4 · 7.52B · unknown
Aug 24, 2026 · Apple M1 Pro
Global Score
34 vs 87
Hardware Fit
58 vs 100
Quality Score
23 vs 82
Hardware
qwen3.5:latest hf.co/unsloth/gemm…
MachineMac miniMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM16 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:latest hf.co/unsloth/gemm…
Tokens/sec13.335.0
First chunk438 ms204 ms
TTFT19.8 s204 ms
Load time0.2 s3.9 s
Memory usage8.0 GB4.9 GB
Memory %50%31%
HW Fit Score Breakdown
qwen3.5:latest
Speed
32/50
TTFT
1/20
Memory
25/30
hf.co/unsloth/gemma-4-E…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3.5:latest
Reasoning
6/20
Coding
1/20
Instruction
3/20
Structured
0/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong
hf.co/unsloth/gemma-4-E…
Reasoning
14/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
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