Back to leaderboard

glm-4.7-flash:q4_K_M

OLLAMA GGUF

glm4moelite · 29.9B · Q4_K_M

Excellent

Mar 7, 2026 · Intel Core™ i5-14600KF

qwen3:30b-a3b-instruct-2507-q4_K_M

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Not Rec.

Jul 31, 2026 · Intel Xeon® E5-4620 0

Global Score
81 vs 71
Hardware Fit
89 vs 42
Quality Score
77 vs 84

Hardware

glm-4.7-flash:q4_K_M qwen3:30b-a3b-inst…
MachineASUSDell Inc. PowerEdge R820
CPUIntel Core™ i5-14600KFIntel Xeon® E5-4620 0
Cores2064
RAM32 GB256 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERMicrosoft Remote Display Adapter, Microsoft Basic Display Adapter
OSMicrosoft Windows 11 Famille 10.0.26200Microsoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modebalancedbalanced

Performance

glm-4.7-flash:q4_K_M qwen3:30b-a3b-inst…
Tokens/sec35.14.0
First chunk440 ms2070 ms
TTFT440 ms2.1 s
Load time11.6 s44.5 s
Memory usage18.4 GB17.7 GB
Memory %58%7%

HW Fit Score Breakdown

glm-4.7-flash:q4_K_M

Speed
49/50
TTFT
20/20
Memory
20/30

qwen3:30b-a3b-instruct-…

Speed
3/50
TTFT
9/20
Memory
30/30

Quality

glm-4.7-flash:q4_K_M

Reasoning
13/20
Coding
17/20
Instruction
12/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

qwen3:30b-a3b-instruct-…

Reasoning
18/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong 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