Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Marginal

Mar 11, 2026 · Apple M4

amd-olmo-1b-sft

LM-STUDIO GGUF

olmo · 1B · Q4_K_M

Marginal

Mar 8, 2026 · Intel Core™ i5-5300U

Global Score
59 vs 44
Hardware Fit
65 vs 75
Quality Score
57 vs 30

Hardware

qwen3.5-9b-mlx amd-olmo-1b-sft
MachineMac miniLENOVO 20BUS00700
CPUApple M4Intel Core™ i5-5300U
Cores104
RAM24 GB16 GB
GPUApple M4Intel(R) HD Graphics 5500
OSmacOS 26.3Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5-9b-mlx amd-olmo-1b-sft
Tokens/sec14.39.2
First chunk24 ms2093 ms
TTFT13.4 s2.1 s
Load time13.3 sN/A
Memory usage2.5 GB0.7 GB
Memory %10%4%

HW Fit Score Breakdown

qwen3.5-9b-mlx

Speed
32/50
TTFT
3/20
Memory
30/30

amd-olmo-1b-sft

Speed
30/50
TTFT
19/20
Memory
26/30

Quality

qwen3.5-9b-mlx

Reasoning
10/20
Coding
17/20
Instruction
5/20
Structured
9/15
Math
11/15
Multilingual
5/10
Reasoning: Weak Coding: Strong Instruction Following: Weak Structured Output: Adequate Math: Adequate Multilingual: Adequate

amd-olmo-1b-sft

Reasoning
4/20
Coding
2/20
Instruction
11/20
Structured
9/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Poor

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