Back to leaderboard

stablelm-2-zephyr-1.6b

LM-STUDIO GGUF

stablelm · 1.6B · Q4_K_M

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

qwen/qwen3.5-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q6_K

Not Rec.

Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
35 vs 72
Hardware Fit
61 vs 35
Quality Score
24 vs 88

Hardware

stablelm-2-zephyr-… qwen/qwen3.5-35b-a3b
MachineLENOVO 20BUS00700System manufacturer
CPUIntel Core™ i5-5300UAMD Ryzen 7 5800X 8-Core Processor
Cores416
RAM16 GB32 GB
GPUIntel(R) HD Graphics 5500AMD Radeon RX 9060 XT
OSMicrosoft Windows 10 Professionnel 10.0.19045Microsoft Windows 11 Home 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

stablelm-2-zephyr-… qwen/qwen3.5-35b-a3b
Tokens/sec6.58.3
First chunk3080 ms32 ms
TTFT3.1 s2.0 s
Load timeN/AN/A
Memory usage1.0 GB28.9 GB
Memory %6%91%

HW Fit Score Breakdown

stablelm-2-zephyr-1.6b

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

qwen/qwen3.5-35b-a3b

Speed
13/50
TTFT
17/20
Memory
5/30

Quality

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

qwen/qwen3.5-35b-a3b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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