deadbydawn101 · text

gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit

deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit

gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit at Q4_K_M is exactly 5,335,285,280 bytes (4.97 GiB / 5.34 GB) — an effective 5.677 bits per weight, not the nominal 4. Its KV cache at 32K is 0.51 GiB, not the 2.63 GiB a flat formula predicts.

From the file· summed from 1 file(s)From the file· KV per layer
Parameters
7.5B
Architecture
gemma4
42 layers
Context
131,072
native (config.json)
License
gemma

Shipped quantizations

● exact bytes, summed from published files
QuantSize●Exact bytes●Effective bpw●Tensors●Publisher
Q4_K_M4.97 GiB5,335,285,2805.677—deadbydawn101
Q5_K_M5.37 GiB5,762,907,6806.132—deadbydawn101
Q8_07.48 GiB8,031,235,6168.546—deadbydawn101
F1614.02 GiB15,053,090,33616.018—deadbydawn101

KV cache by context

computed per layer — this model uses sliding-window attention
ContextKV cache (f16)●Flat formulaOverstated byFull / windowed / recurrent
4,0960.12 GiB0.33 GiB2.67×7 / 35 / 0
8,1920.18 GiB0.66 GiB3.69×7 / 35 / 0
16,3840.29 GiB1.31 GiB4.57×7 / 35 / 0
32,7680.51 GiB2.63 GiB5.19×7 / 35 / 0
65,5360.94 GiB5.25 GiB5.57×7 / 35 / 0
131,0721.82 GiB10.50 GiB5.77×7 / 35 / 0

35 of 42 layers cache only a 512-token window rather than the full context, on a period of . Figures assume the default configuration; --swa-full disables the saving entirely.

Compare with

same modality, comparable size
vs Qwen3-Coder-30B-A3B-Instructvs Qwen3.6-27Bvs Qwen3.8-27Bvs gemma-4-12B-it-qat-q4_0-unquantizedvs gemma-4-E4B-itvs Qwen3-30B-A3B-Thinking-2507All alternatives →Will it fit on my card? →

Will it run on your card?

full quant x context sweep
By VRAM:8GB12GB16GB24GB32GB48GB
Radeon RX 6500 XT 4GBGeForce RTX 3050 6GBGeForce RTX 5050 8GBGeForce RTX 3080 10GBGeForce RTX 2080 Ti 11GBGeForce RTX 5070 12GBGeForce RTX 5060 Ti 16GBApple M3 Pro 18GBGeForce RTX 3080 Ti 20GBGeForce RTX 5090 D V2 24GBGeForce RTX 5090 D 32GBApple M5 Max 36GBApple M5 Pro 48GBApple M5 Max 64GBApple M3 Ultra 96GBApple M5 Max 128GBApple M2 Ultra 192GBApple M3 Ultra 256GBApple M3 Ultra 512GB

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q4_K_M at roughly 3.94 GiB. The real file is 4.97 GiB, because a quantization is a mixture and some tensors are always kept at higher precision. The larger discrepancy is the cache: a flat formula gives 2.63 GiB at 32K context where the real figure is 0.51 GiB, because most of this model's layers cache a fixed window rather than the whole context.

Architecture

from config.json
Layers
42
Attention heads
8
KV heads
2
Head dim
256
Hidden size
2560
Vocab
262,144
Sliding window
512
SWA period
—
MLA
no
Experts
—
Experts per token
—
use_sliding_window
—

Questions people ask

How much VRAM does gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit need?
Q4_K_M is exactly 5,335,285,280 bytes (4.97 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit's KV cache?
0.51 GiB at 32K context with an f16 cache, computed per layer. Quantizing the cache to q8_0 roughly halves it, which is often the difference between a context length fitting and not.
Which quantization of gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit should I use?
Q4_K_M is the usual default. Pick the largest quantization that fits your card at the context you actually need — the table above gives exact sizes for every one published.