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

laguna-xs-2.1

OLLAMA GGUF
Excellent

Aug 1, 2026 · AMD RYZEN AI MAX+ 395

Global Score
45 vs 84
Hardware Fit
54 vs 100
Quality Score
41 vs 77

Hardware

vanilj/palmyra-fin… laguna-xs-2.1
MachineAZW GTR ProAZW GTR Pro
CPUAMD RYZEN AI MAX+ 395AMD RYZEN AI MAX+ 395
Cores3232
RAM125 GB125 GB
GPURadeon 8060SRadeon 8060S
OSUbuntu 24.04.4 LTSUbuntu 24.04.4 LTS
Archx64x64
Power Modelow-powerlow-power

Performance

vanilj/palmyra-fin… laguna-xs-2.1
Tokens/sec6.865.9
First chunk692 ms281 ms
TTFT692 ms281 ms
Load time0.2 s9.9 s
Memory usage27.9 GB30.1 GB
Memory %22%24%

HW Fit Score Breakdown

vanilj/palmyra-fin-70b-…

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

laguna-xs-2.1

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

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

laguna-xs-2.1

Reasoning
8/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
11/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View vanilj/palmyra-fin… details | View laguna-xs-2.1 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