Back to leaderboard

vanilj/palmyra-fin-70b-32k:IQ2_XXS

OLLAMA GGUF

llama · 70.6B · IQ2_XXS

Not Rec.

Aug 5, 2026 · AMD RYZEN AI MAX+ 395

qwen3-coder:30b-a3b-q8_0

OLLAMA GGUF

qwen3moe · 30.5B · Q8_0

Good

Jun 18, 2026 · AMD Ryzen 5 5500U

Global Score
45 vs 78
Hardware Fit
54 vs 54
Quality Score
41 vs 88

Hardware

vanilj/palmyra-fin… qwen3-coder:30b-a3…
MachineAZW GTR ProHP HP Pavilion Laptop 15-eh1xxx
CPUAMD RYZEN AI MAX+ 395AMD Ryzen 5 5500U
Cores3212
RAM125 GB63 GB
GPURadeon 8060SAMD Radeon(TM) Graphics
OSUbuntu 24.04.4 LTSMicrosoft Windows 10 Enterprise LTSC 10.0.19044
Archx64x64
Power Modelow-powerbalanced

Performance

vanilj/palmyra-fin… qwen3-coder:30b-a3…
Tokens/sec6.88.0
First chunk692 ms1468 ms
TTFT692 ms1.5 s
Load time0.2 s114.5 s
Memory usage27.9 GB33.5 GB
Memory %22%53%

HW Fit Score Breakdown

vanilj/palmyra-fin-70b-…

Speed
6/50
TTFT
18/20
Memory
30/30

qwen3-coder:30b-a3b-q8_0

Speed
11/50
TTFT
19/20
Memory
24/30

Quality

vanilj/palmyra-fin-70b-…

Reasoning
7/20
Coding
2/20
Instruction
14/20
Structured
11/15
Math
0/15
Multilingual
7/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Adequate

qwen3-coder:30b-a3b-q8_0

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View vanilj/palmyra-fin… details | View qwen3-coder:30b-a3… 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