How much VRAM does Huihui-GLM-4.5-Air-abliterated-lossytensors need?

I1-Q2_K is exactly 44,972,830,080 bytes (41.88 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is Huihui-GLM-4.5-Air-abliterated-lossytensors's KV cache?

5.75 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 Huihui-GLM-4.5-Air-abliterated-lossytensors a mixture-of-experts model?

Yes — 128 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.

concedo · text · mixture of experts

Huihui-GLM-4.5-Air-abliterated-lossytensors

concedo/Huihui-GLM-4.5-Air-abliterated-lossytensors

Huihui-GLM-4.5-Air-abliterated-lossytensors at I1-Q2_K is exactly 44,972,830,080 bytes (41.88 GiB / 44.97 GB) — an effective 3.257 bits per weight, not the nominal 1. Its KV cache at 32K is 5.75 GiB.

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

Parameters

110B

total, not active

Architecture

glm4moe

46 layers

Context

131,072

native (config.json)

License

mit

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
I1-Q2_K	41.88 GiB	44,972,830,080	3.257	—	mradermacher
I1-IQ3_XS	46.34 GiB	49,755,168,128	3.603	—	mradermacher

KV cache by context

computed per layer

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	0.72 GiB	0.72 GiB	—	46 / 0 / 0
8,192	1.44 GiB	1.44 GiB	—	46 / 0 / 0
16,384	2.88 GiB	2.88 GiB	—	46 / 0 / 0
32,768	5.75 GiB	5.75 GiB	—	46 / 0 / 0
65,536	11.50 GiB	11.50 GiB	—	46 / 0 / 0
131,072	23.00 GiB	23.00 GiB	—	46 / 0 / 0

Compare with

same modality, comparable size

vs Qwen3-Coder-30B-A3B-Instruct vs Qwen3.6-27B vs Qwen3.8-27B vs DeepSeek-V4-Flash vs Qwen3-30B-A3B-Thinking-2507 vs Laguna-XS-2.1 All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts I1-Q2_K at roughly 57.87 GiB. The real file is 41.88 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

128

Hidden size

4096

Vocab

151,552

Sliding window

none

SWA period

—

MLA

Experts

128

Experts per token

use_sliding_window

—

Questions people ask

How much VRAM does Huihui-GLM-4.5-Air-abliterated-lossytensors need?: I1-Q2_K is exactly 44,972,830,080 bytes (41.88 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is Huihui-GLM-4.5-Air-abliterated-lossytensors's KV cache?: 5.75 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 Huihui-GLM-4.5-Air-abliterated-lossytensors a mixture-of-experts model?: Yes — 128 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 Huihui-GLM-4.5-Air-abliterated-lossytensors 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.