Back to leaderboard

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

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor

lmstudio-community/gemma-4-e4b-it-qat

LM-STUDIO GGUF

gemma4 · Q4_0

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score
88 vs 77
Hardware Fit
94 vs 68
Quality Score
85 vs 81

Hardware

huihui-qwen3.6-35b… lmstudio-community…
MachineGigabyte Technology Co., Ltd. B550M AORUS PRODocker Container
CPUAMD Ryzen 5 5600X 6-Core ProcessorIntel Gen Intel® Core™ i9-11900H
Cores1216
RAM47 GB15 GB
GPUAD106 [GeForce RTX 4060 Ti]TigerLake-H GT1 [UHD Graphics]
OScachyos rollingUbuntu 26.04 LTS
Archx64x64
Power Modelow-powerperformance

Performance

huihui-qwen3.6-35b… lmstudio-community…
Tokens/sec39.811.4
First chunk3 ms28 ms
TTFT479 ms2.2 s
Load timeN/A6.8 s
Memory usage24.4 GB0.6 GB
Memory %52%4%

HW Fit Score Breakdown

huihui-qwen3.6-35b-a3b-…

Speed
50/50
TTFT
20/20
Memory
24/30

lmstudio-community/gemm…

Speed
21/50
TTFT
17/20
Memory
30/30

Quality

huihui-qwen3.6-35b-a3b-…

Reasoning
18/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

lmstudio-community/gemm…

Reasoning
14/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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