huihui-ai · text

Llama-3.3-70B-Instruct-abliterated-finetuned

huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned

Llama-3.3-70B-Instruct-abliterated-finetuned at Q4_K_M is exactly 42,520,403,456 bytes (39.60 GiB / 42.52 GB) — an effective 4.821 bits per weight, not the nominal 4.

From the file· summed from 4 file(s)
Parameters
70.6B
Architecture
llama
Context
—
native (config.json)
License
—

Shipped quantizations

● exact bytes, summed from published files
QuantSize●Exact bytes●Effective bpw●Tensors●Publisher
Q2_K24.56 GiB26,375,117,9202.991—DevQuasar-5
Q3_K_M31.91 GiB34,267,503,7123.886—DevQuasar-5
Q4_K_M4 shards39.60 GiB42,520,403,4564.821—DevQuasar-5
Q5_K_M4 shards46.52 GiB49,949,826,5605.664—DevQuasar-5
Q6_K5 shards53.91 GiB57,888,153,2166.564—DevQuasar-5
Q8_06 shards69.83 GiB74,975,059,7128.501—DevQuasar-5

Compare with

same modality, comparable size
vs Qwen3-Coder-30B-A3B-Instructvs Qwen3.6-27Bvs Qwen3.8-27Bvs gemma-4-E4B-itvs Qwen3-30B-A3B-Thinking-2507vs Qwen3-8BAll 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 36.96 GiB. The real file is 39.60 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 Llama-3.3-70B-Instruct-abliterated-finetuned need?
Q4_K_M is exactly 42,520,403,456 bytes (39.60 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of Llama-3.3-70B-Instruct-abliterated-finetuned 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.