llmrun
ZyphraZaya1VLForConditionalGeneration

ZAYA1 VL 8B — Hardware Requirements & GPU Compatibility

Vision

ZAYA1-VL-8B serves as Zyphra's vision-language model with roughly 8 billion total parameters. It builds on the ZAYA1-8B language model, using a Qwen2.5-VL vision encoder. The card outlines two key changes: LoRA parameters specific to vision that activate only when image tokens are present, and bidirectional attention across those same tokens. According to the card, it contains roughly 0.7 billion active parameters, was trained exclusively on open data, and shows strong performance for its scale—scoring 92.5 on DocVQA and 87.5 on AI2D. At this size, quantization allows the model to fit on a single consumer GPU. The context window spans 32,768 tokens. Released under the Apache 2.0 license, it permits unrestricted commercial and research use. Published in April 2026, this release extends the ZAYA1 base text model to handle image understanding tasks.

9.7B params · MoE0.7B active33K contextApache 2.0338.3K downloads42 likes242 quant downloads
S

Runs great on a 24 GB GPU

Runs from8 GB Q4_K_M · 16KBest on24 GB Q4_K_M · ~346 tok/s · 32KMacs from16 GB Q4_K_M · ~89 tok/s

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run ZAYA1 VL 8B

One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.

Recommended

Ollama
one command · needs Ollama installed
$ollama run hf.co/1bit-MONSTER/ZAYA1-VL-8B-GGUF:Q4_K_M

Q4_K_M fits fully on the RTX 4090 · 16.5 GB free · 16K context

Download: ZAYA1-VL-8B-Q4_K_M.gguf5.71 GB1bit-MONSTER

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Your own private copy · Q4_K_M · 24 GB GPU

  • The easiest way to try this model
  • Running in a few minutes, easy setup
  • Chat right here or connect any app

$5+ bonus for new users

How Much VRAM Does ZAYA1 VL 8B Need?

Select a quantization level; the listed hardware adheres to it.

QuantizationVRAM+32KOn RTX 4090 (reference)
4.6 GB7.1 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 32K context · ~370 tok/s
5.2 GB7.7 GB3-bit medium — 3-bit medium quantizationFits: 32K context · ~361 tok/s
6.3 GB8.8 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 32K context · ~346 tok/s
7.4 GB9.9 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 32K context · ~332 tok/s
8.5 GB11 GB6-bit, very good — 6-bit quantization, very good qualityFits: 32K context · ~319 tok/s
10.2 GB12.7 GB8-bit, near-lossless — 8-bit quantization, near-losslessFits: 32K context · ~301 tok/s
19.9 GB22.4 GB16-bit · bfloat — Brain floating point 16 — preferred for trainingFits: 32K context · ~228 tok/s
est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

7.5GBat 16K context

Weights
5.8 GB
KV cache
1.3 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 16.5 GB free · ~346 tok/s

≥50 tok/s needs ≥39 GB/s · RTX 5090 ~386, RTX 3090 Ti ~346

Which Hardware Can Run ZAYA1 VL 8B?

Q4_K_M · 6.3 GB

ZAYA1 VL 8B (Q4_K_M) requires 6.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 9+ GB is recommended. Using the full 33K context window can add up to 2.5 GB, bringing total usage to 8.8 GB. 95 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti. 172 devices with unified memory can run ZAYA1 VL 8B, including NVIDIA RTX Spark N1X Laptop (128 GB), NVIDIA RTX Spark N1X Laptop (32 GB), NVIDIA Jetson Orin Nano 8GB (Super).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8 GB · RTX 4060Q4_K_M · 7.5 GB · ~210 tok/s · 16K8 GB tier →
12 GB · RTX 3060 12GBQ4_K_M · 7.5 GB · ~242 tok/s · 32K12 GB tier →
16 GB · RTX 5060 Ti 16GBQ4_K_M · 7.5 GB · ~266 tok/s · 32K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 7.5 GB · ~346 tok/s · 32K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 7.5 GB · ~75 tok/s · 32KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 7.5 GB · ~109 tok/s · 32KMacs →

Alternatives to ZAYA1 VL 8B

Similar models

6
ModelScoreVRAMtok/sWhy it is similar
Qwen3.5 9BAlibaba99.46.6 GB~103same size
Gemma 2 9B ITGoogle68.07.3 GB~107same size
Ornith 1.5 9Bornith-ai—6.6 GB~103same size
MiniCPM O 4 5OpenBMB—8.3 GB~105same size
GLM 4.1V 9B ThinkingZ.ai—7.2 GB~100same size
Shieldgemma 9BGoogle—8.8 GB~107same size

Specifications

Publisher
Zyphra
Parameters
9.7B
Active parameters
0.7B per token
Architecture
Zaya1VLForConditionalGeneration
Context Length
32,768 tokens
Vocabulary Size
262,272
Release Date
2026-04-20
License
Apache 2.0

Frequently Asked Questions

How much VRAM does ZAYA1 VL 8B need?

ZAYA1 VL 8B requires 6.3 GB of VRAM at Q4_K_M, or 19.9 GB at BF16. Full 33K context adds up to 2.5 GB (8.8 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 9.7B × 4.8 bits ÷ 8 = 5.8 GB

KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)

Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.

KV Cache + Overhead ≈ 3 GB (at full 33K context)

VRAM usage by quantization

6.3 GB
8.8 GB

Learn more about VRAM estimation →

What's the best quantization for ZAYA1 VL 8B?

For ZAYA1 VL 8B, Q4_K_M (6.3 GB) offers the best balance of quality and VRAM usage. Q5_K_M (7.4 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 4.6 GB.

VRAM requirement by quantization

Q2_K
4.6 GB
Q4_K_M ★
6.3 GB
Q5_K_M
7.4 GB
Q6_K
8.5 GB
Q8_0
10.2 GB
BF16
19.9 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run ZAYA1 VL 8B on a Mac?

Yes — Mac Mini M2 Pro (16 GB) and 145 other Macs can run ZAYA1 VL 8B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 6.3 GB of usable unified memory (RAM minus macOS overhead).

Can I run ZAYA1 VL 8B locally?

Yes — ZAYA1 VL 8B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is ZAYA1 VL 8B?

At Q4_K_M, ZAYA1 VL 8B can reach ~124 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~346 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)

Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.

Example: NVIDIA B200 → 0.5 GB active ÷ (8000 × 0.65) = 0.09 ms, plus 40 layers × 0.055 ms = 2.20 ms, so 1000 ÷ 2.29 ms = ~437 tok/s

Estimated speed at Q4_K_M (6.3 GB)

~437 tok/s
~346 tok/s
~437 tok/s
~427 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of ZAYA1 VL 8B?

At Q4_K_M, the download is about 5.83 GB. The full-precision BF16 version is 19.44 GB. The smallest option (Q2_K) is 4.13 GB.

Which GPUs can run ZAYA1 VL 8B?

95 consumer GPUs can run ZAYA1 VL 8B at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6700M, AMD Radeon RX 6750 XT, AMD Radeon RX 5700 XT. 51 GPUs have plenty of headroom for comfortable inference.

Which devices can run ZAYA1 VL 8B?

172 devices with unified memory can run ZAYA1 VL 8B at Q4_K_M (6.3 GB), including AMD Ryzen 7 8845HS (Hawk Point) Laptop, AMD Ryzen AI 7 350 (Krackan Point) Laptop, AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.