MaziyarPanahi · text

Llama-3-8B-Instruct-32k-v0.1

MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1

Llama-3-8B-Instruct-32k-v0.1 at Q4_K_M is exactly 4,920,734,208 bytes (4.58 GiB / 4.92 GB) — an effective 4.902 bits per weight, not the nominal 4.

From the file· summed from 1 file(s)
Parameters
8.0B
Architecture
llama
Context
—
native (config.json)
License
—

Shipped quantizations

● exact bytes, summed from published files
QuantSize●Exact bytes●Effective bpw●Tensors●Publisher
IQ1_S1.88 GiB2,019,627,5202.012—MaziyarPanahi
IQ1_M2.01 GiB2,161,971,7122.154—MaziyarPanahi
IQ2_XS2.43 GiB2,605,781,5042.596—MaziyarPanahi
Q2_K2.96 GiB3,179,131,3923.167—MaziyarPanahi
IQ3_XS3.28 GiB3,518,747,1363.506—MaziyarPanahi
Q3_K_S3.41 GiB3,664,499,2003.651—MaziyarPanahi
Q3_K_M3.74 GiB4,018,917,8884.004291MaziyarPanahi
Q3_K_L4.03 GiB4,321,956,3524.306—MaziyarPanahi
IQ4_XS4.14 GiB4,447,662,5924.431291MaziyarPanahi
Q4_K_S4.37 GiB4,692,668,9284.675—MaziyarPanahi
Q4_K_M4.58 GiB4,920,734,2084.902291MaziyarPanahi
Q5_K_S5.21 GiB5,599,293,9525.578—MaziyarPanahi
Q5_K_M5.34 GiB5,732,987,3925.711291MaziyarPanahi
Q6_K6.14 GiB6,596,006,4006.571291MaziyarPanahi
Q8_07.95 GiB8,540,770,8168.509291MaziyarPanahi

Compare with

same modality, comparable size
vs gemma-4-E4B-itvs Qwen3-4Bvs Qwen3-8Bvs HyperCLOVAX-SEED-Text-Instruct-1.5Bvs Llama-3.2-1B-Instructvs Qwen3-VL-8B-Instruct-abliterated-v1All alternatives →Will it fit on my card? →

Will it run on your card?

full quant x context sweep
By VRAM:8GB12GB16GB24GB32GB48GB
Radeon RX 6400 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 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 4.21 GiB. The real file is 4.58 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-3-8B-Instruct-32k-v0.1 need?
Q4_K_M is exactly 4,920,734,208 bytes (4.58 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-3-8B-Instruct-32k-v0.1 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.