Back to leaderboard

huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 13, 2026 · AMD Ryzen 5 5600X 6-Core Processor

gemma4:e2b

OLLAMA GGUF

gemma4 · 5.1B · Q4_K_M

Good

May 24, 2026 · Intel Gen Intel® Core™ i7-1355U

Global Score
88 vs 72
Hardware Fit
85 vs 71
Quality Score
89 vs 72

Hardware

huihui-qwen3.6-35b… gemma4:e2b
MachineGigabyte Technology Co., Ltd. B550M AORUS PRODell Inc. Inspiron 15 3530
CPUAMD Ryzen 5 5600X 6-Core ProcessorIntel Gen Intel® Core™ i7-1355U
Cores1212
RAM47 GB31 GB
GPUAD106 [GeForce RTX 4060 Ti]Raptor Lake-P [Iris Xe Graphics]
OScachyos rollingcachyos rolling
Archx64x64
Power Modelow-powerlow-power

Performance

huihui-qwen3.6-35b… gemma4:e2b
Tokens/sec37.710.8
First chunk18 ms1408 ms
TTFT2.9 s1.4 s
Load timeN/A6.0 s
Memory usage26.1 GB7.2 GB
Memory %56%23%

HW Fit Score Breakdown

huihui-qwen3.6-35b-a3b-…

Speed
50/50
TTFT
13/20
Memory
22/30

gemma4:e2b

Speed
21/50
TTFT
20/20
Memory
30/30

Quality

huihui-qwen3.6-35b-a3b-…

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

gemma4:e2b

Reasoning
10/20
Coding
16/20
Instruction
14/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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