Complete Multi-Axis Analysis — Agent Model Selection on Mac Mini M4 16GB
Date: 2026-04-08 | Tests: 6 agent tasks × 15+ configurations | Vision: Falcon Perception v2
Axis Overview
5 axes tested across 15+ model configurations:
Axis 1: Model Family ─── Qwen3.5-9B vs Gemma4-E4B vs Qwen3VL-8B vs Bonsai vs others
Axis 2: Censoring ────── Base (censored) vs Uncensored (Balanced vs Aggressive)
Axis 3: Quantization ─── Q4 vs Q5 vs Q6 vs Q8 vs 1-bit vs BF16/4bit-MLX
Axis 4: Backend ──────── llama.cpp (GGUF) vs mlx_vlm (MLX) vs Ollama vs PrismML
Axis 5: Vision ──────── with mmproj vs without vs Falcon Perception detector
AXIS 1: Model Family
Score Speed Multi-step Form Fill Vision Min Params
(/6) (tok/s) Chains? Works? Detect? for Agent
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Qwen3.5-9B (9B dense) 5.0 13.5 ✅ Yes ✅ Yes ✅ FP 9B
Gemma4 E4B (4B MoE) 5.0 24.5 ✅ Yes ✅ Yes ✅ FP 4B active
Qwen3VL-8B (8B dense) 3.0 16.2 ⚠️ Crashes ❌ Crashed ✅ FP 8B
Bonsai-8B (8B 1-bit) 1.0 48.8 ❌ 1 turn ❌ No ❌ No 8B (degraded)
LFM2.5-Nova (1.2B) 0.0 118.4 ❌ 1 turn ❌ No ❌ No 1.2B
FunctionGemma (270M) 0.0 197.0 ❌ Loops ❌ No ❌ No 270M
Qwopus-27B Q3 (27B) OOM OOM ❌ OOM ❌ OOM ❌ OOM 27B (too big)
INSIGHT: The agent capability cliff is at ~4B active params.
Below 4B: can format tool calls but cannot chain them.
Above 4B: can navigate, search, fill forms, use vision.
Model FAMILY matters less than active parameter count.
Gemma4 (4B active MoE) matches Qwen3.5 (9B dense).
Family Comparison (best variant of each)
Score vs Speed:
5.0 │ ★ Qwen3.5 Unc Q6K ★ Gemma4 Unc Q5KP
│ (13.5 tok/s) (24.5 tok/s)
4.0 │
│
3.0 │ ★ Qwen3VL Bal Q6K
│ (16.2 tok/s)
2.0 │
│
1.0 │ ★ Bonsai
│ (48.8 tok/s)
0.0 │ ★ LFM2.5 ★ FuncGemma
└──────┬──────────┬──────────┬──────────┬──────────┬──────────┬
10 20 30 50 118 197
Speed (tok/s)
AXIS 2: Censoring (Base vs Uncensored)
┌────────────────────────┬───────────┬───────────┬───────────┐
│ │ Base │Uncensored │Uncensored │
│ │ (censor) │ Balanced │ Aggressive│
├────────────────────────┼───────────┼───────────┼───────────┤
│ Qwen3.5-9B Q4 score │ 4.5/6 │ — │ 3.5/6 ↓ │
│ Qwen3.5-9B Q6 score │ — │ — │ 5.0/6 ★ │
│ Gemma4 E4B Q6 score │ — │ — │ 4.5/6 │
│ Gemma4 E4B Q5 score │ — │ — │ 5.0/6 ★ │
│ Qwen3VL-8B Q6 score │ — │ 3.0/6 │ — │
│ │ │ │ │
│ Tool call reliability │ Good │ Similar │ Better │
│ Refusal rate │ Some │ Zero │ Zero │
│ Stop discipline │ Good │ Similar │ Better │
│ Form fill success │ ✅ │ — │ ✅ │
└────────────────────────┴───────────┴───────────┴───────────┘
INSIGHT: Uncensoring does NOT directly improve agent tasks.
The improvement we see (3.5→5.0 for Qwen Q4→Q6) is
from QUANTIZATION, not censoring.
Base Qwen3.5-9B Q4_K_XL (4.5/6) vs
Uncensored Q4_K_M (3.5/6) → uncensored is WORSE at Q4.
The uncensored Q6_K (5.0/6) wins because Q6 > Q4,
not because uncensored > censored.
Uncensoring helps with: content generation, creative tasks.
Uncensoring neutral for: tool calling, agent planning.
Uncensoring harmful at: Q4 level (less reliable stops).
AXIS 3: Quantization
Gemma4 E4B Uncensored — Quant Ladder
┌─────────┬────────┬────────┬───────┬───────┬───────┬───────┐
│ Quant │ Size │ Memory │Speed │Score │Stops │Tools │
│ │ (GB) │ (GB) │tok/s │ (/6) │ (/6) │ total │
├─────────┼────────┼────────┼───────┼───────┼───────┼───────┤
│ Q5_K_P │ 5.4 │ 6.3 │ 24.5 │ 5.0 ★ │ 3 ★ │ 50 │
│ Q6_K_P │ 5.8 │ 6.7 │ 23.1 │ 4.5 │ 2 │ 52 ★ │
│ Q8_K_P │ 7.6 │ 8.5 │ 19.0 │ 4.0 │ 2 │ 41 │
│ 4bit MLX│ ~5.0 │ 5.4 │ 35.0★ │ 4.5 │ 1 │ 29 │
└─────────┴────────┴────────┴───────┴───────┴───────┴───────┘
Speed vs Score:
Score 5.0 │ ★ Q5_K_P
│
4.5 │ ★ Q6_K_P ★ 4bit-MLX
│
4.0 │ ★ Q8_K_P
│
3.5 │
└──┬────────┬────────┬────────┬────
19 23 25 35
Speed (tok/s)
INSIGHT: Higher quantization ≠ better agent performance!
Q5 > Q6 > Q8 for agent tasks. Why?
1. Q5 is FASTER → more turns per timeout → more work done
2. Q5 has enough precision for tool call JSON formatting
3. Q8 wastes memory on precision the model can't use for reasoning
4. The bottleneck is REASONING DEPTH (4B params), not PRECISION
SWEET SPOT: Q5_K_P — best score, fastest, smallest
Qwen3.5-9B Uncensored — Quant Ladder
┌─────────┬────────┬────────┬───────┬───────┬───────┐
│ Quant │ Size │ Memory │Speed │Score │Stops │
├─────────┼────────┼────────┼───────┼───────┼───────┤
│ Q4_K_M │ 5.2 │ 6.1 │ 16.7 │ 3.5 │ 0 │
│ Q6_K │ 6.9 │ 7.8 │ 13.5 │ 5.0 ★ │ 2 ★ │
│ Q8_0 │ 8.9 │ ~10 │ ~10 │ N/A │ N/A │
│ Base Q4 │ 5.6 │ 6.5 │ 10.0 │ 4.5 │ 2 │
└─────────┴────────┴────────┴───────┴───────┴───────┘
INSIGHT: For Qwen (9B dense), HIGHER quant IS better.
Q4 (3.5) → Q6 (5.0) = massive improvement.
The 9B dense model has more capacity that benefits
from higher precision. Unlike the 4B MoE Gemma4 where
the bottleneck is active params not precision.
SWEET SPOT: Q6_K — best score, fits 16GB
Cross-Model Quant Pattern
FINDING: Optimal quantization depends on active parameter count.
Dense 9B (Qwen): Q4 < Q6 ★ (precision limited, higher=better)
MoE 4B (Gemma4): Q5 ★ > Q6 > Q8 (speed limited, faster=better)
1-bit 8B (Bonsai): Degraded regardless (1-bit destroys reasoning)
Rule of thumb:
• Dense models: use highest quant that fits
• MoE models: use mid quant (Q5) for best speed/quality
• Ultra-small quant (<Q4): breaks multi-step reasoning
AXIS 4: Backend
┌──────────────────┬──────────────────────────────────────────────────────┐
│ Backend │ Characteristics │
├──────────────────┼──────────────────────────────────────────────────────┤
│ llama.cpp (GGUF) │ ✅ Native tool calling for Qwen + Gemma4 │
│ (stock homebrew) │ ✅ No proxy needed │
│ │ ✅ mmproj vision support │
│ │ ✅ Best compatibility with LlmTornado │
│ │ ⚠️ Slower than MLX for MoE models │
│ │ Speed: 10-25 tok/s depending on model │
├──────────────────┼──────────────────────────────────────────────────────┤
│ mlx_vlm (MLX) │ ★ Fastest for Gemma4 MoE (35 tok/s) │
│ │ ❌ Needs proxy for LlmTornado (7 fixes!) │
│ │ ❌ Streaming tool calls broken │
│ │ ❌ Content array format incompatible │
│ │ ❌ Screenshot images break chat format │
│ │ Speed: 35 tok/s (but proxy overhead) │
├──────────────────┼──────────────────────────────────────────────────────┤
│ Ollama │ ✅ Easy model management │
│ │ ✅ Native Gemma4 tool calling via /api/chat │
│ │ ❌ OpenAI compat layer drops tool calls for Gemma4 │
│ │ ❌ Message format issues with LlmTornado │
│ │ Speed: ~35 tok/s (Gemma4 E4B) │
├──────────────────┼──────────────────────────────────────────────────────┤
│ PrismML fork │ ✅ Required for Bonsai 1-bit GGUF │
│ (llama.cpp) │ ❌ Older version, missing Qwen3.5 mmproj support │
│ │ Speed: 49 tok/s (Bonsai) │
└──────────────────┴──────────────────────────────────────────────────────┘
Backend Decision Tree:
Is model Qwen3.5 or Gemma4 GGUF?
YES → llama.cpp (stock) ★ BEST — native everything, no proxy
NO →
Is model Gemma4 MLX and speed critical?
YES → mlx_vlm + proxy (35 tok/s but complex)
NO →
Is model Bonsai 1-bit?
YES → PrismML llama.cpp fork
NO → Ollama (easiest but compatibility issues)
INSIGHT: llama.cpp (stock GGUF) is the clear winner for agent tasks.
Native tool calling, no proxy, best LlmTornado compat.
The 35 tok/s MLX advantage isn't worth the proxy complexity.
Gemma4 GGUF on llama.cpp (23 tok/s) > Gemma4 MLX (35 tok/s)
because reliability > raw speed for agent tasks.
AXIS 5: Vision Configuration
┌─────────────────────────┬──────────┬──────────────────────────────────────┐
│ Configuration │ Score │ How vision works │
├─────────────────────────┼──────────┼──────────────────────────────────────┤
│ mmproj only (VLM sees │ 4.5/6 │ LLM sees screenshots directly. │
│ screenshots directly) │ │ Slow: 30-40s to process each image. │
│ │ │ Inaccurate: misidentifies objects. │
│ │ │ Uses all context for image tokens. │
├─────────────────────────┼──────────┼──────────────────────────────────────┤
│ Falcon Perception only │ 4.5/6 │ Dedicated 0.6B detector. │
│ (no mmproj, text-only │ │ Fast: 2s per detection. │
│ LLM + vision_detect) │ │ Returns pixel coordinates. │
│ │ │ LLM never sees images — saves ctx. │
├─────────────────────────┼──────────┼──────────────────────────────────────┤
│ mmproj + Falcon (both) │ 5.0/6 ★ │ Best of both worlds: │
│ │ │ • LLM sees screenshots (understands │
│ │ │ page layout, text, context) │
│ │ │ • Falcon detects objects precisely │
│ │ │ (captcha grids, UI elements) │
│ │ │ • 3-layer adaptive pipeline routes │
│ │ │ to best method per task │
├─────────────────────────┼──────────┼──────────────────────────────────────┤
│ No vision at all │ 1-2/6 │ Model can only navigate + extract │
│ (text-only, no images) │ │ text. Can't interact with visual UI. │
└─────────────────────────┴──────────┴──────────────────────────────────────┘
Falcon Perception 3-Layer Pipeline:
Layer 1 (Router): "captcha" → detection (2s)
"measure" → segmentation (5-9s)
Layer 2 (Present): default → coordinates text (fastest)
verify → cropped images for VLM
spatial → Set-of-Marks overlay
Layer 3 (Extract): coords: "[1] center=(211,155)"
crops: 3 JPEG images per detection
overlay: annotated full image
INSIGHT: mmproj + Falcon together > either alone.
mmproj lets the LLM understand page context.
Falcon gives pixel-accurate object detection.
The combination scores 5.0/6 vs 4.5/6 for either alone.
Memory cost: Falcon = 1.5GB always loaded.
Speed cost: 2s per vision_detect call (negligible vs LLM).
THE COMPLETE PICTURE
All Tested Configurations Ranked
Rank Model + Config Score Speed Memory Proxy Backend
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
1. Gemma4 Unc Q5_K_P +mm +FP 5.0/6 24.5 6.3G No llama.cpp
2. Qwen3.5 Unc Q6_K +mm +FP 5.0/6 13.5 7.8G No llama.cpp
3. Gemma4 Unc Q6_K_P +mm +FP 4.5/6 23.1 6.7G No llama.cpp
4. Gemma4 Base 4bit +FP 4.5/6 35.0 5.4G YES mlx_vlm
5. Qwen3.5 Base Q4_K_XL +mm +FP 4.5/6 10.0 6.5G No llama.cpp
6. Gemma4 Unc Q8_K_P +mm +FP 4.0/6 19.0 8.5G No llama.cpp
7. Qwen3.5 Unc Q4_K_M +mm +FP 3.5/6 16.7 6.1G No llama.cpp
8. Qwen3VL Bal Q6_K +mm +FP 3.0/6 16.2 7.4G No llama.cpp
9. Bonsai-8B 1-bit +FP 1.0/6 48.8 1.5G No PrismML
10. LFM2.5-Nova 1.2B Q4 0.0/6 118.4 0.8G No llama.cpp
11. FunctionGemma 270M Q8 0.0/6 197.0 0.3G No llama.cpp
12. Qwopus-27B Q3_K_S OOM OOM 14.0G No llama.cpp
+mm = with mmproj | +FP = with Falcon Perception
Key Decisions
┌─────────────────────────────────────────────────────────────────────┐
│ DECISION FRAMEWORK │
│ │
│ Q: Which model? │
│ A: Gemma4 E4B Uncensored Q5_K_P │
│ • Tied #1 at 5.0/6, fastest winner (24.5 tok/s) │
│ • 1.5GB smaller than Qwen alternative │
│ • No proxy needed (GGUF on llama.cpp) │
│ • Form filling works (the Gemma4 MLX version couldn't) │
│ │
│ Q: Which quantization? │
│ A: For MoE (Gemma4): Q5_K_P (speed > precision) │
│ For Dense (Qwen): Q6_K (precision > speed) │
│ Never Q8+ (wastes memory, slower, no quality gain) │
│ Never Q4 or below (breaks multi-step reasoning) │
│ │
│ Q: Which backend? │
│ A: llama.cpp (stock homebrew) for everything │
│ MLX only if you need 35 tok/s AND accept proxy complexity │
│ │
│ Q: Censored or uncensored? │
│ A: Doesn't matter for agent tasks. Quality comes from quant. │
│ Uncensored helps if tasks involve restricted content. │
│ │
│ Q: What about vision? │
│ A: Always use mmproj + Falcon Perception together (5.0/6) │
│ Either alone = 4.5/6. Both = synergy. │
│ │
│ Q: Can we get 6/6? │
│ A: T2 (DDG) and T6 (CAPTCHA) timeout — model works but │
│ doesn't stop in time. Improving stop_loop instructions │
│ or extending timeouts would push to 5.5-6.0/6. │
│ The model DOES the work — it just keeps going. │
└─────────────────────────────────────────────────────────────────────┘
Counter-Intuitive Findings
1. BFCL ≠ Agent Capability
Bonsai: 73% BFCL but 1.0/6 agents (single-turn ≠ multi-turn)
2. Bigger Quant ≠ Better Agent (for MoE)
Gemma4: Q5 (5.0) > Q6 (4.5) > Q8 (4.0) — speed wins over precision
3. Bigger Quant = Better Agent (for Dense)
Qwen: Q4 (3.5) < Q6 (5.0) — precision matters for 9B dense
4. Uncensored ≠ Better Agent
Same model, same quant: uncensored doesn't improve tool calling
5. Faster Backend ≠ Better Results
Gemma4 MLX (35 tok/s, 4.5) < Gemma4 GGUF (24 tok/s, 5.0)
Proxy complexity and message format issues hurt more than speed helps
6. 270M → 9B Speed Inversion
FunctionGemma (197 tok/s, 0/6) < Gemma4 (24 tok/s, 5/6)
10x faster but completely useless for the actual task
7. 4B Active Params = 9B Dense
Gemma4 MoE (4B active) matches Qwen (9B dense) on agent tasks
MoE architecture is incredibly efficient for tool calling
Memory & Disk Reference
16GB Mac Mini M4 — Memory Budget:
Gemma4 Q5_K_P (winner):
Model: 5.4 GB ████████████████████████████
mmproj: 0.9 GB █████
Falcon: 1.5 GB ████████
GUA+Brwsr: 0.8 GB ████
OS: 3.0 GB ████████████████
KV Cache: ~1.5 GB ████████
─────────────────────────────────
Total: 13.1 GB Free: 2.9 GB ✅
Qwen Q6_K (runner-up):
Model: 6.9 GB ████████████████████████████████████
mmproj: 0.9 GB █████
Falcon: 1.5 GB ████████
GUA+Brwsr: 0.8 GB ████
OS: 3.0 GB ████████████████
KV Cache: ~1.5 GB ████████
─────────────────────────────────
Total: 14.6 GB Free: 1.4 GB ⚠️ tight
15+ configurations tested across 5 axes, 90+ individual test runs. Mac Mini M4 16GB (Dyson), April 3-8 2026.