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

OLLAMA GGUF

llama · 70.6B · IQ2_XXS

Not Rec.

Aug 5, 2026 · AMD RYZEN AI MAX+ 395

qwen3-4b-qwen3.6-plus-reasoning-distilled

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

Global Score

45 vs 65

Hardware Fit

54 vs 96

Quality Score

41 vs 51

Hardware

vanilj/palmyra-fin… qwen3-4b-qwen3.6-p…

MachineAZW GTR ProMac Studio

CPUAMD RYZEN AI MAX+ 395Apple M2 Max

Cores3212

RAM125 GB96 GB

GPURadeon 8060SApple M2 Max

OSUbuntu 24.04.4 LTSmacOS 26.1

Archx64arm64

Power Modelow-powerbalanced

Performance

vanilj/palmyra-fin… qwen3-4b-qwen3.6-p…

Tokens/sec6.899.6

First chunk692 ms18 ms

TTFT692 ms1.6 s

Load time0.2 s4.8 s

Memory usage27.9 GB0.3 GB

Memory %22%0%

HW Fit Score Breakdown

vanilj/palmyra-fin-70b-…

Speed

6/50

TTFT

18/20

Memory

30/30

qwen3-4b-qwen3.6-plus-r…

Speed

50/50

TTFT

16/20

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

qwen3-4b-qwen3.6-plus-r…

Reasoning

8/20

Coding

4/20

Instruction

14/20

Structured

9/15

Math

8/15

Multilingual

8/10

Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Adequate Multilingual: Strong

View vanilj/palmyra-fin… details | View qwen3-4b-qwen3.6-p… 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