FitMyLLM
Alibaba/Dense

AlibabaQwen 3.5 0.8B

Qwen 3.5 0.8B — tiny multimodal model for edge devices. Vision, 262K context, 201 languages.

chatcodingmultilingualvision
0.8B
Parameters
256K
Context length
4
Benchmarks
6
Quantizations
2.0M
HF downloads
Architecture
Dense
Released
2026-03-01
Layers
24
KV Heads
2
Head Dim
256
Family
qwen

Quantization Options

QuantBitsVRAMQuality
Q4_K_M4.891.0 GBgood
Q5_K_S5.571.0 GBgood
Q5_K_M5.71.1 GBgood
Q6_K6.561.1 GBexcellent
Q8_08.51.3 GBlossless
FP16162.1 GBlossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Benchmarks (4)

MMBench69.9
IFEval52.1
MMMU49.0
MMLU-PRO29.7

Run this model

Easiest way to get starteddocs →
curl -fsSL https://ollama.com/install.sh | sh
$ollama run qwen3.5:0.8b:q4_k_m

Downloads and runs automatically. Add --verbose for speed stats.

Setup guide
HuggingFaceOllama LibraryGGUF DownloadsBuild Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

AMD FireGL V7350
1 GB VRAM • 41.6 GB/s
AMD
NVIDIA Quadro FX 5500
1 GB VRAM • 32.3 GB/s
NVIDIA
NVIDIA Quadro FX 5500 SDI
1 GB VRAM • 32.3 GB/s
NVIDIA
AMD Stream Processor
1 GB VRAM • 41.5 GB/s
AMD
AMD FireGL V8600
1 GB VRAM • 111.1 GB/s
AMD
NVIDIA GeForce 9600 GT Mac Edition
1 GB VRAM • 17 GB/s
NVIDIA
NVIDIA GeForce 9600M GS
1 GB VRAM • 25.6 GB/s
NVIDIA
NVIDIA GeForce 9650M GT
1 GB VRAM • 25.6 GB/s
NVIDIA
NVIDIA GeForce 9800M GTS
1 GB VRAM • 51.2 GB/s
NVIDIA
NVIDIA GeForce 9800M GTX
1 GB VRAM • 51.2 GB/s
NVIDIA
NVIDIA GeForce GTX 280
1 GB VRAM • 141.7 GB/s
NVIDIA
NVIDIA GeForce GTX 285
1 GB VRAM • 159 GB/s
NVIDIA
NVIDIA Quadro FX 3700M
1 GB VRAM • 51.2 GB/s
NVIDIA
NVIDIA Quadro FX 3800M
1 GB VRAM • 64 GB/s
NVIDIA
NVIDIA Quadro FX 4700 X2
1 GB VRAM • 51.2 GB/s
NVIDIA
AMD FireStream 9250
1 GB VRAM • 63.5 GB/s
AMD
AMD FirePro V8700
1 GB VRAM • 108.8 GB/s
AMD
AMD Radeon HD 4570
1 GB VRAM • 8 GB/s
AMD
AMD Radeon HD 4710
1 GB VRAM • 25.6 GB/s
AMD
AMD Radeon HD 4730 OEM
1 GB VRAM • 25.3 GB/s
AMD
AMD Radeon HD 4870 X2
1 GB VRAM • 115.2 GB/s
AMD
NVIDIA GeForce 210 OEM
1 GB VRAM • 6.4 GB/s
NVIDIA
NVIDIA GeForce 210 Rev. 2
1 GB VRAM • 6.4 GB/s
NVIDIA
NVIDIA GeForce G110M
1 GB VRAM • 11.2 GB/s
NVIDIA
NVIDIA GeForce GT 120M
1 GB VRAM • 16 GB/s
NVIDIA
NVIDIA GeForce GT 130M
1 GB VRAM • 25.6 GB/s
NVIDIA
NVIDIA GeForce GT 140 OEM
1 GB VRAM • 57.6 GB/s
NVIDIA
NVIDIA GeForce GT 220
1 GB VRAM • 22.4 GB/s
NVIDIA
NVIDIA GeForce GT 220M
1 GB VRAM • 16 GB/s
NVIDIA
NVIDIA GeForce GT 230M
1 GB VRAM • 25.3 GB/s
NVIDIA

Find the best GPU for Qwen 3.5 0.8B

Build Hardware for Qwen 3.5 0.8B

Qwen 3.5 0.8B — 0.8B Parameter Dense LLM

Model Specifications

Parameters
0.8B
Architecture
Dense Transformer
Context Length
256K tokens
Capabilities
chat, coding, multilingual, vision
Release Date
2026-03-01
Provider
Alibaba
Family
qwen

VRAM Requirements

QuantizationBPWVRAMQuality
Q4_K_M4.891.0 GB94%
Q5_K_S5.571.0 GB96%
Q5_K_M5.71.1 GB96%
Q6_K6.561.1 GB97%
Q8_08.51.3 GB100%
FP16162.1 GB100%

Benchmark Scores

MMLU-PRO29.7
IFEval52.1
MMMU49.0
MMBench69.9

How to Run Qwen 3.5 0.8B

Run Qwen 3.5 0.8B locally with Ollama (needs 1.0 GB VRAM at Q4_K_M):

ollama run qwen3.5:0.8b

Compatible GPUs (30)

GPUs that can run Qwen 3.5 0.8B at Q4_K_M quantization:

AMD FireGL V7350(1GB, 41.6 GB/s)NVIDIA Quadro FX 5500(1GB, 32.3 GB/s)NVIDIA Quadro FX 5500 SDI(1GB, 32.3 GB/s)AMD Stream Processor(1GB, 41.5 GB/s)AMD FireGL V8600(1GB, 111.1 GB/s)NVIDIA GeForce 9600 GT Mac Edition(1GB, 17 GB/s)NVIDIA GeForce 9600M GS(1GB, 25.6 GB/s)NVIDIA GeForce 9650M GT(1GB, 25.6 GB/s)NVIDIA GeForce 9800M GTS(1GB, 51.2 GB/s)NVIDIA GeForce 9800M GTX(1GB, 51.2 GB/s)NVIDIA GeForce GTX 280(1GB, 141.7 GB/s)NVIDIA GeForce GTX 285(1GB, 159 GB/s)NVIDIA Quadro FX 3700M(1GB, 51.2 GB/s)NVIDIA Quadro FX 3800M(1GB, 64 GB/s)NVIDIA Quadro FX 4700 X2(1GB, 51.2 GB/s)