Back to leaderboard

qwen3:32b

OLLAMA GGUF

qwen3 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

qwen3.6-35b-a3b-claude-4.7-opus-reasoning-distilled-apex

LM-STUDIO GGUF

qwen35moe · 35B

Not Rec.

Aug 19, 2026 · Apple M4 Max

Global Score
79 vs 88
Hardware Fit
59 vs 80
Quality Score
88 vs 92

Hardware

qwen3:32b qwen3.6-35b-a3b-cl…
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M4 Max
Cores2016
RAM122 GB128 GB
GPUDevice 2e12Apple M4 Max
OSUbuntu 24.04.4 LTSmacOS 26.5.2
Archarm64arm64
Power Modeperformancebalanced

Performance

qwen3:32b qwen3.6-35b-a3b-cl…
Tokens/sec9.776.7
First chunk324 ms29 ms
TTFT324 ms30.0 s
Load time24.5 sN/A
Memory usage26.8 GB23.9 GB
Memory %22%19%

HW Fit Score Breakdown

qwen3:32b

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

qwen3.6-35b-a3b-claude-…

Speed
50/50
TTFT
0/20
Memory
30/30

Quality

qwen3:32b

Reasoning
19/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.6-35b-a3b-claude-…

Reasoning
19/20
Coding
18/20
Instruction
17/20
Structured
14/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3:32b details | View qwen3.6-35b-a3b-cl… 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