qwen3.6:35b-mlx
OLLAMA GGUFnvfp4
Jul 17, 2026 · Apple M5 Max
codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
Global Score
80 vs 67
Hardware Fit
77 vs 67
Quality Score
81 vs 67
Hardware
qwen3.6:35b-mlx codestral:22b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M5 MaxCortex-X925
Cores1820
RAM48 GB122 GB
GPUApple M5 MaxDevice 2e12
OSmacOS 26.5.2Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
qwen3.6:35b-mlx codestral:22b
Tokens/sec129.817.2
First chunk77 ms129 ms
TTFT30.0 s129 ms
Load time1.8 s11.6 s
Memory usage19.7 GB18.9 GB
Memory %41%16%
HW Fit Score Breakdown
qwen3.6:35b-mlx
Speed
50/50
TTFT
0/20
Memory
27/30
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
Quality
qwen3.6:35b-mlx
Reasoning
19/20
Coding
9/20
Instruction
18/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Adequate Math: Strong Multilingual: Strong
codestral:22b
Reasoning
11/20
Coding
17/20
Instruction
9/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Weak 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