Back to leaderboard

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

LM-STUDIO GGUF

qwen35moe · 35B

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
90 vs 35
Hardware Fit
98 vs 61
Quality Score
86 vs 24

Hardware

qwen3.6-35b-a3b-cl… 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

qwen3.6-35b-a3b-cl… stablelm-2-zephyr-…
Tokens/sec86.66.5
First chunk13 ms3080 ms
TTFT143 ms3.1 s
Load timeN/AN/A
Memory usage23.9 GB1.0 GB
Memory %37%6%

HW Fit Score Breakdown

qwen3.6-35b-a3b-claude-…

Speed
50/50
TTFT
20/20
Memory
28/30

stablelm-2-zephyr-1.6b

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

Quality

qwen3.6-35b-a3b-claude-…

Reasoning
18/20
Coding
17/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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 qwen3.6-35b-a3b-cl… 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