Only with CPU offload
GLM-4.7-Flash 30B-A3B at Q4_K_M needs 18.6 GB but only 7.0 GB is addressable, so about 66% of the layers would stream from system RAM at roughly 60 GB/s. Expect around 12 tokens per second — usable for batch work, painful for chat.
MIT-licensed 30B-A3B tuned for agentic coding, with a DeepSeek-style latent KV cache. 60–80 tok/s reported on a 4090.
Hardware requirements What hardware do I need to run GLM-4.7-Flash 30B-A3B? →At Q4_K_M with an 8K context: a 24 GB GPU (RTX 4090) or a 32 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 30.9 GB | 31.9 GB | — | ~5.7 | −0.1% ppl | 24.9 GB over |
| Q6_K | 23.8 GB | 24.8 GB | — | ~7.8 | −0.4% ppl | 17.8 GB over |
| Q5_K_M | 20.6 GB | 21.6 GB | — | ~9.5 | −0.8% ppl | 14.6 GB over |
| Q4_K_M | 17.5 GB | 18.6 GB | — | ~12 | −1.9% ppl | 11.6 GB over |
| Q3_K_M | 14.2 GB | 15.2 GB | — | ~16 | −5.4% ppl | 8.2 GB over |
| Q2_K | 12.2 GB | 13.2 GB | — | ~21 | −15% ppl | 6.2 GB over |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. This model uses multi-head latent attention, so its cache is a compressed latent rather than full K and V.
How to run it
$ llama-server \
-hf zai-org/GLM-4.7-Flash:Q4_K_M \
-c 8192 -ngl 16
The engine underneath most of the others. Every knob is exposed. More on llama.cpp.
Related models on an Arc A750
| Model | Total | Tok/s est. | |
|---|---|---|---|
| GLM-5.3-Flash 320B-A18B 321B MoE · same family |
Q4_K_M · 181.2 GB | ~1.4 | CPU offload |
| GLM-5.2 744B-A40B 753B MoE · same family |
Q4_K_M · 424.7 GB | — | Won't fit |
| GLM-5.3 744B-A40B 753B MoE · same family |
Q4_K_M · 424.7 GB | — | Won't fit |
| Gemma 4 31B 31.3B · similar size |
Q4_K_M · 20.2 GB | ~2.6 | CPU offload |
| Nemotron 3.5 Lightning 30B-A3B 31.6B MoE · similar size |
Q4_K_M · 18.4 GB | ~11 | CPU offload |
| Qwen3 30B-A3B 30.5B MoE · similar size |
Q4_K_M · 18.5 GB | ~11 | CPU offload |
| Qwen3 Coder 30B-A3B 30.5B MoE · similar size |
Q4_K_M · 18.5 GB | ~11 | CPU offload |
GLM-4.7-Flash 30B-A3B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
18.6 GB | ~11 | CPU offload |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
18.6 GB | ~15 | CPU offload |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
18.6 GB | — | Won't fit |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
18.6 GB | 139 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
18.6 GB | 133 | Runs great |
| M4 · 32 GB 24.0 GB usable · 120 GB/s |
18.6 GB | 19 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
18.6 GB | 62 | Runs great |