Can Desktop PC · GeForce RTX 4080 SUPER · 32 GB RAM run GLM-4.7-Flash (30B-A3B)?
16 GB VRAM + 32 GB RAM · 736 GB/s memory bandwidth · GLM-4.7-Flash (30B-A3B) has 31.2B parameters (3B active per token).
Short answer
It loads, but it's borderline even for chat.
Best quantization for chat: Q4_K_M (17 GB of weights) on Ollama. Generation: 60–85 tok/s, leaving about 0.0 GB free for your other apps.
How it rates for each workload
Same model and machine, different jobs. Agents and long documents send far bigger prompts than chat, so they need much more speed and memory.
| Workload | Verdict | Quant | Generation | First reply | Context | |
|---|---|---|---|---|---|---|
| Chatwith Open WebUI | Borderline | Q4_K_M | 60–85 tok/s | under 1 s | 8K | Details |
| Coding questionswith Continue | Borderline | Q4_K_M | 50–70 tok/s | ≈2 s | 16K | Details |
| Coding in a repositorywith Aider | Borderline | Q4_K_M | 35–50 tok/s | ≈6 s | 32K | Details |
| Agentic codingwith OpenCode | Borderline | Q4_K_M | 35–45 tok/s | ≈9 s | 32K | Details |
| Long documents (64K)with Open WebUI | Borderline | Q4_K_M | 17–25 tok/s | ≈40 s | 64K | Details |
Speeds are estimates calibrated against measured benchmarks on similar hardware. “First reply” is the time to read the workload’s opening prompt. How we calculate
Get it running
Copy-paste commands for the Q4_K_M build with a 8K context. Ollama and llama.cpp download the file straight from Hugging Face.
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:Q4_K_M
Downloads 18.31 GB (Q4_K_M). Ollama's default context is small: set OLLAMA_CONTEXT_LENGTH=8192 before `ollama serve` for long prompts.
Other models for Desktop PC · GeForce RTX 4080 SUPER · 32 GB RAM
The best-rated models for chat on this machine.
- gpt-oss-20b≈170 tok/sExcellent
- Gemma 4 26B-A4B170–230 tok/sExcellent
- MiniCPM5 2B160–210 tok/sExcellent
- Qwen3.5 9B55–70 tok/sExcellent
- Qwen3.5 4B95–130 tok/sExcellent
- Gemma 4 12B45–60 tok/sExcellent
Cheapest machines for GLM-4.7-Flash (30B-A3B)
Hardware rated comfortable or better for chat, lowest price first.
- Laptop · Ryzen AI 9 HX 370 (Radeon 890M) · 32 GB$1,300 · 25–40 tok/sComfortable
- Laptop · Core Ultra 7 258V (Arc 140V) · 32 GB$1,300 · 20–35 tok/sComfortable
- Mac mini M4 32 GB$1,399 · 30–40 tok/sExcellent
- Desktop PC · Ryzen 9 9950X (no GPU) · 64 GB DDR5$1,400 · 10–17 tok/sComfortable
- Desktop PC · Intel Arc Pro B60 24GB · 32 GB RAM$1,500 · 70–120 tok/sExcellent
- Ryzen AI Max+ 395 mini PC / Framework Desktop · 64 GB$1,600 · 55–75 tok/sExcellent
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.