How much VRAM does Ourbox-35B-JGOS need?

Q4_K_M is exactly 21,166,757,536 bytes (19.71 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is Ourbox-35B-JGOS's KV cache?

0.63 GiB at 32K context with an f16 cache, computed per layer from the model's architecture. Quantizing the cache to q8_0 roughly halves it.

Is Ourbox-35B-JGOS a mixture-of-experts model?

Yes — 256 experts with 8 routed per token. Every expert must be resident in memory, but only the routed ones are read per token, so its memory requirement and its speed behave very differently.

FINAL-Bench · text · mixture of experts

Ourbox-35B-JGOS

FINAL-Bench/Ourbox-35B-JGOS

Ourbox-35B-JGOS at Q4_K_M is exactly 21,166,757,536 bytes (19.71 GiB / 21.17 GB) — an effective 4.886 bits per weight, not the nominal 4. Its KV cache at 32K is 0.63 GiB.

From the file· summed from 1 file(s)From the file· KV per layer

Parameters

34.7B

total, not active

Architecture

qwen35moe

40 layers

Context

262,144

native (config.json)

License

apache-2.0

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
IQ1_M	7.67 GiB	8,239,208,288	1.902	—	FINAL-Bench
Q2_K	12.05 GiB	12,939,593,376	2.987	—	FINAL-Bench
Q3_K_M	15.61 GiB	16,764,763,808	3.869	—	FINAL-Bench
Q4_K_M	19.71 GiB	21,166,757,536	4.886	—	FINAL-Bench

KV cache by context

computed per layer

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	0.08 GiB	0.31 GiB	4.00×	10 / 0 / 30
8,192	0.16 GiB	0.63 GiB	4.00×	10 / 0 / 30
16,384	0.31 GiB	1.25 GiB	4.00×	10 / 0 / 30
32,768	0.63 GiB	2.50 GiB	4.00×	10 / 0 / 30
65,536	1.25 GiB	5.00 GiB	4.00×	10 / 0 / 30
131,072	2.50 GiB	10.00 GiB	4.00×	10 / 0 / 30

30 of 40 layers use linear attention, which keeps a fixed-size recurrent state instead of a per-token cache. Those layers do not grow with context at all — treating them as ordinary attention, as a flat formula does, overstates this model's cache by roughly 4.0× at long context.

Compare with

same modality, comparable size

vs Qwen3-Coder-30B-A3B-Instruct vs Qwen3.6-27B vs Qwen3.8-27B vs gemma-4-12B-it-qat-q4_0-unquantized vs gemma-4-E4B-it vs Qwen3-30B-A3B-Thinking-2507 All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q4_K_M at roughly 18.16 GiB. The real file is 19.71 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

Architecture

from config.json

Layers

Attention heads

KV heads

Head dim

256

Hidden size

2048

Vocab

248,320

Sliding window

none

SWA period

—

MLA

Experts

256

Experts per token

use_sliding_window

—

Questions people ask

How much VRAM does Ourbox-35B-JGOS need?: Q4_K_M is exactly 21,166,757,536 bytes (19.71 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is Ourbox-35B-JGOS's KV cache?: 0.63 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.
Is Ourbox-35B-JGOS a mixture-of-experts model?: Yes — 256 experts, 8 routed per token. Every expert must be resident, but only the routed ones are read per token, which is why its memory requirement and its speed behave very differently.
Which quantization of Ourbox-35B-JGOS 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.