zandenAI · text · gated

GLM-5.2-FP8-Uncensored

zandenAI/GLM-5.2-FP8-Uncensored

GLM-5.2-FP8-Uncensored at Q4_K_M is exactly 454,552,363,264 bytes (423.33 GiB / 454.55 GB) — an effective 4.827 bits per weight, not the nominal 4.

From the file· summed from 11 file(s)
Parameters
753B
Architecture
glm-dsa
Context
—
native (config.json)
License
mit

Shipped quantizations

● exact bytes, summed from published files
QuantSize●Exact bytes●Effective bpw●Tensors●Publisher
IQ2_M7 shards276.94 GiB297,361,733,4403.158—phaseonx11
IQ3_XXS9 shards341.07 GiB366,220,601,3763.889—phaseonx11
IQ4_XS10 shards373.42 GiB400,955,277,5044.258—phaseonx11
Q4_K_M11 shards423.33 GiB454,552,363,2644.827—phaseonx11
Q6_K15 shards576.10 GiB618,583,923,4886.569—phaseonx11
Q8_020 shards745.78 GiB800,777,319,4568.503—phaseonx11
BF1638 shards1403.43 GiB1,506,919,578,88016.002—phaseonx11

Compare with

same modality, comparable size
vs DeepSeek-V4-Flashvs DeepSeek-V4-Flash-0731vs Laguna-S-2.1vs Hy3vs GLM-5.2vs Qwen3-Coder-NextAll 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 394.67 GiB. The real file is 423.33 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

Architecture

Architecture unavailable — this repository is gated and no ungated mirror was found. Exact file sizes above are still authoritative; only the KV math needs the config.

Questions people ask

How much VRAM does GLM-5.2-FP8-Uncensored need?
Q4_K_M is exactly 454,552,363,264 bytes (423.33 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of GLM-5.2-FP8-Uncensored 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.