Back to leaderboard

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

LM-STUDIO GGUF

qwen35moe · 35B

Excellent

Jun 19, 2026 · AMD Ryzen 5 5600X 6-Core Processor

lmstudio-community/gemma-4-e4b-it

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

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

Global Score
89 vs 76
Hardware Fit
90 vs 67
Quality Score
88 vs 80

Hardware

qwen3.6-35b-a3b-cl… 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

qwen3.6-35b-a3b-cl… lmstudio-community…
Tokens/sec42.210.8
First chunk40 ms44 ms
TTFT2.7 s2.0 s
Load timeN/A10.9 s
Memory usage21.9 GB0.0 GB
Memory %47%0%

HW Fit Score Breakdown

qwen3.6-35b-a3b-claude-…

Speed
50/50
TTFT
14/20
Memory
26/30

lmstudio-community/gemm…

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

Quality

qwen3.6-35b-a3b-claude-…

Reasoning
19/20
Coding
16/20
Instruction
14/20
Structured
14/15
Math
15/15
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
16/20
Structured
15/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong 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