vanilj/palmyra-fin-70b-32k:IQ2_XXS
OLLAMA GGUFllama · 70.6B · IQ2_XXS
Aug 5, 2026 · AMD RYZEN AI MAX+ 395
gemma4:e4b
OLLAMA GGUFgemma4 · 8.0B · Q4_K_M
Apr 3, 2026 · AMD RYZEN AI MAX+ 395
Global Score
45 vs 84
Hardware Fit
54 vs 98
Quality Score
41 vs 78
Hardware
vanilj/palmyra-fin… gemma4:e4b
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-powerperformance
Performance
vanilj/palmyra-fin… gemma4:e4b
Tokens/sec6.853.0
First chunk692 ms214 ms
TTFT692 ms214 ms
Load time0.2 s3.1 s
Memory usage27.9 GB15.0 GB
Memory %22%12%
HW Fit Score Breakdown
vanilj/palmyra-fin-70b-…
Speed
6/50
TTFT
18/20
Memory
30/30
gemma4:e4b
Speed
48/50
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
gemma4:e4b
Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest