How much VRAM does GLM-ASR-Nano-2512 need?

Q4_K is exactly 980,472,032 bytes (0.91 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is GLM-ASR-Nano-2512's KV cache?

1.75 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.

zai-org · audio asr

GLM-ASR-Nano-2512

zai-org/GLM-ASR-Nano-2512

GLM-ASR-Nano-2512 at Q4_K is exactly 980,472,032 bytes (0.91 GiB / 0.98 GB) — an effective 3.474 bits per weight, not the nominal 4. Its KV cache at 32K is 1.75 GiB.

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

Parameters

2.3B

Architecture

glmasr

28 layers

Context

8,192

native (config.json)

License

mit

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q4_K	0.91 GiB	980,472,032	3.474	—	concedo
Q4_K	1.23 GiB	1,325,316,448	4.696	—	cstr
Q8_0	1.58 GiB	1,696,635,104	6.011	—	concedo
Q8_0	2.27 GiB	2,436,544,864	8.633	—	cstr
BF16	2.97 GiB	3,190,364,384	11.304	—	concedo

KV cache by context

computed per layer

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	0.22 GiB	0.22 GiB	—	28 / 0 / 0
8,192	0.44 GiB	0.44 GiB	—	28 / 0 / 0
16,384	0.88 GiB	0.88 GiB	—	28 / 0 / 0
32,768	1.75 GiB	1.75 GiB	—	28 / 0 / 0
65,536	3.50 GiB	3.50 GiB	—	28 / 0 / 0
131,072	7.00 GiB	7.00 GiB	—	28 / 0 / 0

Compare with

same modality, comparable size

vs nemotron-3.5-asr-streaming-0.6b vs parakeet-unified-en-0.6b vs cohere-transcribe-03-2026 vs parakeet-tdt-0.6b-v3 vs whisper-medium vs whisper-large-v3 All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q4_K at roughly 1.18 GiB. The real file is 0.91 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

2048

Vocab

59,264

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

—

Questions people ask

How much VRAM does GLM-ASR-Nano-2512 need?: Q4_K is exactly 980,472,032 bytes (0.91 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is GLM-ASR-Nano-2512's KV cache?: 1.75 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.
Which quantization of GLM-ASR-Nano-2512 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.