FitMyLLM
Zhipu AI/Dense

Zhipu AIGLM-4.1V 9B Thinking

GLM-4.1V 9B Thinking — Zhipu's vision-language reasoning model. Thinking mode is on by default, which is where its benchmark scores come from.

chatvisionreasoningmultilingual
10.29B
Parameters
64K
Context length
3
Benchmarks
10
Quantizations
356K
HF downloads
Architecture
Dense
Released
2025-06-28
Layers
40
KV Heads
2
Head Dim
128
Family
glm

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q3_K_M4
6.1 GB
5.6 + 0.5 KV
low
Q3_K_L4.3
6.5 GB
6.0 + 0.5 KV
moderate
IQ4_XS4.46
6.7 GB
6.2 + 0.5 KV
moderate
Q4_K_S4.67
7.0 GB
6.5 + 0.5 KV
moderate
Q4_K_M4.89
7.2 GB
6.8 + 0.5 KV
good
Q5_K_S5.57
8.1 GB
7.7 + 0.5 KV
good
Q5_K_M5.7
8.3 GB
7.8 + 0.5 KV
good
Q6_K6.56
9.4 GB
8.9 + 0.5 KV
excellent
Q8_08.5
11.9 GB
11.4 + 0.5 KV
lossless
FP1616
21.5 GB
21.1 + 0.5 KV
lossless

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

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
Ready to run this?Rent by the hour

Rent a GPU and run GLM-4.1V 9B Thinking now

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (3)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run hf.co/unsloth/GLM-4.1V-9B-Thinking-GGUF:Q4_K_M

Not in Ollama's library: Ollama pulls the GGUF from Hugging Face (unsloth/GLM-4.1V-9B-Thinking-GGUF). If Q4_K_M is not in that repo, pick a file listed there.

Setup guide
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

Apple M1 (8GB)
8 GB VRAM • 68 GB/s
APPLE
$499
Apple M2 (8GB)
8 GB VRAM • 100 GB/s
APPLE
$599
Apple M3 (8GB)
8 GB VRAM • 100 GB/s
APPLE
$599
NVIDIA Tesla K8
8 GB VRAM • 160 GB/s
NVIDIA
NVIDIA Tesla M60
8 GB VRAM • 160 GB/s
NVIDIA

Find the best GPU for GLM-4.1V 9B Thinking

Build Hardware for GLM-4.1V 9B Thinking
Spec sheet

GLM-4.1V 9B Thinking — 10.29B Dense.

Specifications
Parameters
10.29B
Architecture
Dense Transformer
Context Length
64K tokens
Capabilities
chat, vision, reasoning, multilingual
Release Date
2025-06-28
Provider
Zhipu AI
Family
glm
VRAM requirements
QuantBPWVRAMQuality
Q3_K_M45.6 GB88%
Q3_K_L4.36.0 GB90%
IQ4_XS4.466.2 GB92%
Q4_K_S4.676.5 GB93%
Q4_K_M4.896.8 GB94%
Q5_K_S5.577.7 GB96%
Q5_K_M5.77.8 GB96%
Q6_K6.568.9 GB97%
Q8_08.511.4 GB100%
FP161621.1 GB100%
Benchmark scores
MMMU68.0
MMBench85.8
MMMU Pro57.1
Compatible GPUs
30 @ Q4_K_M