Back to leaderboard

glm-4.7-flash:latest

OLLAMA GGUF

glm4moelite · 29.9B · Q4_K_M

Not Rec.

Mar 22, 2026 · AMD RYZEN AI MAX+ 395

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

Global Score
86 vs 89
Hardware Fit
74 vs 90
Quality Score
91 vs 88

Hardware

glm-4.7-flash:latest qwen3.6-35b-a3b-cl…
MachineAZW GTR ProGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUAMD RYZEN AI MAX+ 395AMD Ryzen 5 5600X 6-Core Processor
Cores3212
RAM125 GB47 GB
GPURadeon 8060SAD106 [GeForce RTX 4060 Ti]
OSUbuntu 24.04.4 LTScachyos rolling
Archx64x64
Power Modeperformancelow-power

Performance

glm-4.7-flash:latest qwen3.6-35b-a3b-cl…
Tokens/sec47.842.2
First chunk194 ms40 ms
TTFT30.0 s2.7 s
Load time7.4 sN/A
Memory usage37.7 GB21.9 GB
Memory %30%47%

HW Fit Score Breakdown

glm-4.7-flash:latest

Speed
44/50
TTFT
0/20
Memory
30/30

qwen3.6-35b-a3b-claude-…

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

Quality

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

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
View glm-4.7-flash:latest details | View qwen3.6-35b-a3b-cl… 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