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

glm-4.7-flash:latest

OLLAMA GGUF

glm4moelite · 29.9B · Q4_K_M

Not Rec.

Mar 22, 2026 · AMD RYZEN AI MAX+ 395

Global Score
88 vs 86
Hardware Fit
94 vs 74
Quality Score
85 vs 91

Hardware

huihui-qwen3.6-35b… glm-4.7-flash:latest
MachineGigabyte Technology Co., Ltd. B550M AORUS PROAZW GTR Pro
CPUAMD Ryzen 5 5600X 6-Core ProcessorAMD RYZEN AI MAX+ 395
Cores1232
RAM47 GB125 GB
GPUAD106 [GeForce RTX 4060 Ti]Radeon 8060S
OScachyos rollingUbuntu 24.04.4 LTS
Archx64x64
Power Modelow-powerperformance

Performance

huihui-qwen3.6-35b… glm-4.7-flash:latest
Tokens/sec39.847.8
First chunk3 ms194 ms
TTFT479 ms30.0 s
Load timeN/A7.4 s
Memory usage24.4 GB37.7 GB
Memory %52%30%

HW Fit Score Breakdown

huihui-qwen3.6-35b-a3b-…

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

glm-4.7-flash:latest

Speed
44/50
TTFT
0/20
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

glm-4.7-flash:latest

Reasoning
19/20
Coding
17/20
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
View huihui-qwen3.6-35b… details | View glm-4.7-flash:latest 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