Back to leaderboard

qwen2.5-coder:32b

OLLAMA GGUF

qwen2 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Excellent

Jul 17, 2026 · Apple M5 Max

Global Score
78 vs 89
Hardware Fit
59 vs 97
Quality Score
86 vs 86

Hardware

qwen2.5-coder:32b qwen3.6:35b-mlx
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M5 Max
Cores2018
RAM122 GB48 GB
GPUDevice 2e12Apple M5 Max
OSUbuntu 24.04.4 LTSmacOS 26.5.2
Archarm64arm64
Power Modeperformancebalanced

Performance

qwen2.5-coder:32b qwen3.6:35b-mlx
Tokens/sec9.5129.4
First chunk394 ms49 ms
TTFT395 ms49 ms
Load time72.1 s0.0 s
Memory usage26.5 GB20.5 GB
Memory %22%43%

HW Fit Score Breakdown

qwen2.5-coder:32b

Speed
9/50
TTFT
20/20
Memory
30/30

qwen3.6:35b-mlx

Speed
50/50
TTFT
20/20
Memory
27/30

Quality

qwen2.5-coder:32b

Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.6:35b-mlx

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen2.5-coder:32b details | View qwen3.6:35b-mlx 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