Skip to content

GLM-4.7 Flash on 4× RTX 3090: VRAM, speed and fit

GLM-4.7 Flash at 8-bit runs on the 4× RTX 3090 with 198K of context at about 130 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on 4× RTX 3090 · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
43.8 GB
of 96.0 GB
Context
198K
auto
Speed
130 tok/s
41 when full
First reply
0.2 s
2K prompt

Where the memory goes

Model
30.9 GB
Context
10.2 GB
Overhead
2.7 GB
OS
0.0 GB
Free
52.2 GB
Memory
43.8 GB of 96.0 GB
Context
198K tokens · auto
Speed
130 tok/s · 41 when full
First reply
0.2 s for a 2K prompt
Running cost
$20/mo at home · $66/mo on a cloud 2× RTX A5000

Validation: Validated

What GLM-4.7 Flash on 4× RTX 3090 was checked against
CheckTargetResultStatus
Fits in GPU memory96.0 GB usable43.8 GB neededPass
Headroom5% free52.2 GB free (54%)Pass
Context for chat16K or more198KPass
Writing speed15 tok/s or more130 tok/sPass
First replyunder 3 s, 2K prompt0.2 sPass

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
GLM-4.7 Flash
Parameters
31.2B, 3B active
Precision
8-bit (Q8_0)
Context
198K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
4× RTX 3090
GPU can use
96.0 GB of 96.0 GB

Running cost

At home
$20/mo
920 W at the wall
Renting instead
$66/mo
2× RTX A5000 at $0.54/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.

How to run it

Ollama
ollama run glm-4.7-flash:latest
llama.cpp
llama-server -hf unsloth/GLM-4.7-Flash-GGUF
vLLM
vllm serve zai-org/GLM-4.7-Flash
MLX (Mac)
mlx_lm.chat --model mlx-community/GLM-4.7-Flash-4bit

GLM-4.7 Flash on similar machines

All machines: GLM-4.7 Flash VRAM requirements. Everything that runs here: what can the 4× RTX 3090 run?

Other models that run on 4× RTX 3090

Questions

Can GLM-4.7 Flash run on 4× RTX 3090?

GLM-4.7 Flash at 8-bit runs on the 4× RTX 3090 with 198K of context at about 130 tokens a second.

Report VR-11UZIWH, calculated Nov 22, 2026 from published specs, not benchmarked.