Back to leaderboard

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

lmstudio-community/gemma-4-26b-a4b-it

LM-STUDIO GGUF

gemma4 · 26B · Q4_K_M

Excellent

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

Global Score
71 vs 81
Hardware Fit
42 vs 56
Quality Score
84 vs 91

Hardware

qwen3:30b-a3b-inst… lmstudio-community…
MachineDell Inc. PowerEdge R820Docker Container
CPUIntel Xeon® E5-4620 0Intel Gen Intel® Core™ i9-11900H
Cores6416
RAM256 GB15 GB
GPUMicrosoft Remote Display Adapter, Microsoft Basic Display AdapterTigerLake-H GT1 [UHD Graphics]
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348Ubuntu 26.04 LTS
Archx64x64
Power Modebalancedperformance

Performance

qwen3:30b-a3b-inst… lmstudio-community…
Tokens/sec4.09.9
First chunk2070 ms145 ms
TTFT2.1 s4.4 s
Load time44.5 s48.3 s
Memory usage17.7 GB5.6 GB
Memory %7%37%

HW Fit Score Breakdown

qwen3:30b-a3b-instruct-…

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

lmstudio-community/gemm…

Speed
18/50
TTFT
10/20
Memory
28/30

Quality

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

lmstudio-community/gemm…

Reasoning
17/20
Coding
19/20
Instruction
18/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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