prithivMLmods · text

Qwen3-VL-8B-Instruct-Unredacted-MAX

prithivMLmods/Qwen3-VL-8B-Instruct-Unredacted-MAX

Qwen3-VL-8B-Instruct-Unredacted-MAX at Q4_K_M is exactly 5,027,785,376 bytes (4.68 GiB / 5.03 GB) — an effective 4.588 bits per weight, not the nominal 4. Its KV cache at 32K is 4.50 GiB.

From the file· summed from 1 file(s)From the file· KV per layer
Parameters
8.8B
Architecture
qwen3vl
36 layers
Context
262,144
native (config.json)
License
apache-2.0

Shipped quantizations

● exact bytes, summed from published files
QuantSize●Exact bytes●Effective bpw●Tensors●Publisher
Q2_K3.06 GiB3,281,734,3042.995—KuroTo4ka
Q2_K3.06 GiB3,281,734,9442.995—mradermacher
Q3_K_S3.51 GiB3,769,613,6003.440—mradermacher
Q3_K_M3.84 GiB4,124,162,7203.763—KuroTo4ka
Q3_K_M3.84 GiB4,124,163,3603.763—mradermacher
Q3_K_L4.13 GiB4,431,395,4884.044—KuroTo4ka
Q3_K_L4.13 GiB4,431,396,1284.044—mradermacher
IQ4_XS4.28 GiB4,593,298,7204.191—mradermacher
Q4_K_S4.47 GiB4,802,013,8564.382—KuroTo4ka
Q4_K_S4.47 GiB4,802,014,4964.382—mradermacher
Q4_K_M4.68 GiB5,027,785,3764.588—KuroTo4ka
Q4_K_M4.68 GiB5,027,786,0164.588—mradermacher
Q5_K_S5.33 GiB5,720,763,0405.220—KuroTo4ka
Q5_K_S5.33 GiB5,720,763,6805.220—mradermacher
Q5_K_M5.45 GiB5,851,114,1445.339—KuroTo4ka
Q5_K_M5.45 GiB5,851,114,7845.339—mradermacher
Q6_K6.26 GiB6,725,900,9606.137—KuroTo4ka
Q6_K6.26 GiB6,725,901,6006.137—mradermacher
Q8_08.11 GiB8,709,519,6487.947—prithivMLmods
Q8_08.11 GiB8,709,520,0327.947—KuroTo4ka
Q8_08.11 GiB8,709,520,6727.947—mradermacher
BF1615.26 GiB16,388,045,08814.954—prithivMLmods
F1615.26 GiB16,388,045,47214.954—KuroTo4ka
F1615.26 GiB16,388,046,11214.954—mradermacher

KV cache by context

computed per layer
ContextKV cache (f16)●Flat formulaOverstated byFull / windowed / recurrent
4,0960.56 GiB0.56 GiB—36 / 0 / 0
8,1921.13 GiB1.13 GiB—36 / 0 / 0
16,3842.25 GiB2.25 GiB—36 / 0 / 0
32,7684.50 GiB4.50 GiB—36 / 0 / 0
65,5369.00 GiB9.00 GiB—36 / 0 / 0
131,07218.00 GiB18.00 GiB—36 / 0 / 0

Compare with

same modality, comparable size
vs Qwen3-Coder-30B-A3B-Instructvs gemma-4-12B-it-qat-q4_0-unquantizedvs gemma-4-E4B-itvs Qwen3-30B-A3B-Thinking-2507vs Qwen3-4Bvs 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 4.59 GiB. The real file is 4.68 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

Architecture

from config.json
Layers
36
Attention heads
32
KV heads
8
Head dim
128
Hidden size
4096
Vocab
151,936
Sliding window
none
SWA period
—
MLA
no
Experts
—
Experts per token
—
use_sliding_window
—

Questions people ask

How much VRAM does Qwen3-VL-8B-Instruct-Unredacted-MAX need?
Q4_K_M is exactly 5,027,785,376 bytes (4.68 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is Qwen3-VL-8B-Instruct-Unredacted-MAX's KV cache?
4.50 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 Qwen3-VL-8B-Instruct-Unredacted-MAX 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.