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

qwen/qwen3.6-35b-a3b

LM-STUDIO MLX

qwen3_5_moe · 35B · 4bit

Excellent

Jul 17, 2026 · Apple M5 Max

Global Score
45 vs 89
Hardware Fit
54 vs 97
Quality Score
41 vs 86

Hardware

vanilj/palmyra-fin… qwen/qwen3.6-35b-a3b
MachineAZW GTR ProMacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M5 Max
Cores3218
RAM125 GB64 GB
GPURadeon 8060SApple M5 Max
OSUbuntu 24.04.4 LTSmacOS 27.0
Archx64arm64
Power Modelow-powerbalanced

Performance

vanilj/palmyra-fin… qwen/qwen3.6-35b-a3b
Tokens/sec6.8130.2
First chunk692 ms5 ms
TTFT692 ms135 ms
Load time0.2 sN/A
Memory usage27.9 GB26.6 GB
Memory %22%42%

HW Fit Score Breakdown

vanilj/palmyra-fin-70b-…

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

qwen/qwen3.6-35b-a3b

Speed
50/50
TTFT
20/20
Memory
27/30

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

qwen/qwen3.6-35b-a3b

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View vanilj/palmyra-fin… details | View qwen/qwen3.6-35b-a3b 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