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

mistralai/ministral-3-3b

LM-STUDIO GGUF

mistral3 · 3B · Q4_K_M

Good

Oct 31, 2026 · AMD RYZEN AI MAX+ 395

Global Score
45 vs 76
Hardware Fit
54 vs 94
Quality Score
41 vs 68

Hardware

vanilj/palmyra-fin… mistralai/ministra…
MachineAZW GTR ProGMKtec EVO-X3
CPUAMD RYZEN AI MAX+ 395AMD RYZEN AI MAX+ 395
Cores3232
RAM125 GB120 GB
GPURadeon 8060SAMD Radeon(TM) 8060S Graphics
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26300
Archx64x64
Power Modelow-powerbalanced

Performance

vanilj/palmyra-fin… mistralai/ministra…
Tokens/sec6.850.2
First chunk692 ms6 ms
TTFT692 ms726 ms
Load time0.2 sN/A
Memory usage27.9 GB19.6 GB
Memory %22%16%

HW Fit Score Breakdown

vanilj/palmyra-fin-70b-…

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

mistralai/ministral-3-3b

Speed
46/50
TTFT
18/20
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

mistralai/ministral-3-3b

Reasoning
10/20
Coding
16/20
Instruction
15/20
Structured
15/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
View vanilj/palmyra-fin… details | View mistralai/ministra… 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