perplexity-ai · text

r1-1776-distill-llama-70b

perplexity-ai/r1-1776-distill-llama-70b

r1-1776-distill-llama-70b at Q4_K_M is exactly 42,520,395,840 bytes (39.60 GiB / 42.52 GB) — an effective 4.821 bits per weight, not the nominal 4.

From the file· summed from 1 file(s)
Parameters
70.6B
Architecture
llama
Context
—
native (config.json)
License
mit

Shipped quantizations

● exact bytes, summed from published files
QuantSize●Exact bytes●Effective bpw●Tensors●Publisher
IQ1_M15.60 GiB16,751,198,7841.899—bartowski
IQ2_XXS17.79 GiB19,097,387,5842.165—bartowski
IQ2_XS19.69 GiB21,142,110,7842.397—bartowski
IQ2_S20.71 GiB22,242,345,5362.522—bartowski
IQ2_M22.46 GiB24,119,296,5762.735—bartowski
Q2_K24.56 GiB26,375,110,7202.991—unsloth
Q2_K24.56 GiB26,375,111,2322.991—bartowski
Q2_K_L24.79 GiB26,621,362,2403.019—unsloth
Q2_K_L25.52 GiB27,401,159,2323.107—bartowski
IQ3_XXS25.58 GiB27,469,496,8963.115—bartowski
IQ3_XS27.29 GiB29,307,732,5443.323—bartowski
Q3_K_S28.79 GiB30,912,053,8243.505—bartowski
IQ3_M29.74 GiB31,937,036,8643.621—bartowski
Q3_K_M31.91 GiB34,267,496,5123.886—unsloth
Q3_K_M31.91 GiB34,267,497,0243.886—bartowski
Q3_K_L34.59 GiB37,140,594,9764.211—lmstudio-community
Q3_K_L34.59 GiB37,140,595,2644.211—bartowski
IQ4_XS35.30 GiB37,902,664,2564.298—bartowski
IQ4_NL37.30 GiB40,053,621,3124.542—bartowski
Q4_037.36 GiB40,116,535,8724.549—bartowski
Q4_K_S37.58 GiB40,347,222,5924.575—bartowski
Q4_K_M39.60 GiB42,520,395,8404.821—unsloth
Q4_K_M39.60 GiB42,520,396,0644.821—lmstudio-community
Q4_K_M39.60 GiB42,520,396,3524.821—bartowski
Q4_K_L40.33 GiB43,300,192,8324.910—bartowski
Q4_141.27 GiB44,313,592,3845.025—bartowski
Q5_K_S45.32 GiB48,657,449,5365.517—bartowski
Q5_K_M46.52 GiB49,949,818,9445.664—unsloth
Q5_K_M2 shards46.52 GiB49,949,819,6805.664—bartowski
Q6_K2 shards53.91 GiB57,888,145,6646.564—unsloth
Q6_K2 shards53.91 GiB57,888,145,8886.564—lmstudio-community
Q6_K2 shards53.91 GiB57,888,146,2086.564—bartowski
Q8_02 shards69.83 GiB74,975,052,0328.501—unsloth
Q8_02 shards69.83 GiB74,975,052,2568.501—bartowski
Q8_02 shards69.83 GiB74,975,052,2568.501—lmstudio-community
BF163 shards131.43 GiB141,117,915,52016.001—unsloth

Compare with

same modality, comparable size
vs Qwen3-Coder-30B-A3B-Instructvs Qwen3.6-27Bvs Qwen3.8-27Bvs gemma-4-12B-it-qat-q4_0-unquantizedvs gemma-4-E4B-itvs Qwen3-30B-A3B-Thinking-2507All 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 r1-1776-distill-llama-70b need?
Q4_K_M is exactly 42,520,395,840 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 r1-1776-distill-llama-70b 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.