Back to leaderboard

qwen/qwen3.6-35b-a3b

LM-STUDIO MLX

qwen3_5_moe · 35B · 4bit

Excellent

Jul 17, 2026 · Apple M5 Max

stablelm-2-zephyr-1.6b

LM-STUDIO GGUF

stablelm · 1.6B · Q4_K_M

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

Global Score
89 vs 35
Hardware Fit
97 vs 61
Quality Score
86 vs 24

Hardware

qwen/qwen3.6-35b-a3b stablelm-2-zephyr-…
MachineMacBook ProLENOVO 20BUS00700
CPUApple M5 MaxIntel Core™ i5-5300U
Cores184
RAM64 GB16 GB
GPUApple M5 MaxIntel(R) HD Graphics 5500
OSmacOS 27.0Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

qwen/qwen3.6-35b-a3b stablelm-2-zephyr-…
Tokens/sec130.26.5
First chunk5 ms3080 ms
TTFT135 ms3.1 s
Load timeN/AN/A
Memory usage26.6 GB1.0 GB
Memory %42%6%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b

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

stablelm-2-zephyr-1.6b

Speed
23/50
TTFT
16/20
Memory
22/30

Quality

qwen/qwen3.6-35b-a3b

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

stablelm-2-zephyr-1.6b

Reasoning
2/20
Coding
2/20
Instruction
8/20
Structured
6/15
Math
2/15
Multilingual
4/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak
View qwen/qwen3.6-35b-a3b details | View stablelm-2-zephyr-… 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