RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can I run GLM 4.7 Flash locally?

GLM 4.7 Flash by zai-org has 31B parameters (4.6B active per token, 64 experts, 4 used per token). At 4-bit with an 8K context it needs about 18.3 GB of GPU memory. It fits on 56 of 65 GPUs and Macs we track. See all models that fit in 24 GB of VRAM.

18.3 GBQ4_K_M · 8K context
RTX 3090smallest consumer GPU that fits
M4 32GBsmallest Mac that fits
198Kmax context
MLAattention type

Memory needed by quant and context length

GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from bartowski/zai-org_GLM-4.7-Flash-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.

QuantQuality4K ctx8K ctx32K ctx128K ctx
2-bit (Q2_K) •rough11.2 GB11.4 GB12.6 GB17.6 GB
3-bit (Q3_K_M) •usable14.0 GB14.2 GB15.5 GB20.4 GB
4-bit (Q4_K_M) •good, most popular18.1 GB18.3 GB19.6 GB24.5 GB
5-bit (Q5_K_M) •very good21.0 GB21.2 GB22.4 GB27.4 GB
6-bit (Q6_K) •near lossless24.0 GB24.2 GB25.5 GB30.4 GB
8-bit (Q8_0) •effectively lossless30.6 GB30.8 GB32.0 GB37.0 GB
16-bit (F16/BF16) •original weights56.7 GB56.9 GB58.1 GB63.1 GB

Which GPUs and Macs run GLM 4.7 Flash?

Best quality quant that fits at 8K context. "Tight" = within 10% of usable memory. Speed is a ceiling from memory bandwidth (real speed is typically 50–80% of it).

HardwareMemoryFits?Best quantNeedsMax tok/s (est.)Details
RTX 3060 12GB12 GBTightQ2_K11.4 GB221details
RTX 4060 Ti 16GB16 GBFitsQ2_K11.4 GB177details
RTX 309024 GBFitsQ4_K_M18.3 GB343details
RTX 409024 GBFitsQ4_K_M18.3 GB370details
RTX 509032 GBFitsQ6_K24.2 GB489details
RTX 5070 Ti16 GBFitsQ2_K11.4 GB550details
RX 7900 XTX24 GBFitsQ4_K_M18.3 GB352details
Mac M4 Pro 48GB48 GBFitsQ6_K24.2 GB74details
Mac M4 Max 128GB128 GBFitsF1656.9 GB62details
Mac M3 Ultra 512GB512 GBFitsF1656.9 GB93details
DGX Spark128 GBFitsF1656.9 GB31details
RTX 407012 GBTightQ2_K11.4 GB309details
RTX 5060 Ti 16GB16 GBFitsQ2_K11.4 GB275details
RTX 40608 GBNo———details
Arc B58012 GBTightQ2_K11.4 GB280details
RTX 3060 Ti8 GBNo———details
RTX 30708 GBNo———details
RTX 3080 10GB10 GBNo———details
RTX 3080 12GB12 GBTightQ2_K11.4 GB560details
RTX 3090 Ti24 GBFitsQ4_K_M18.3 GB370details
RTX 4060 Ti 8GB8 GBNo———details
RTX 4070 Super12 GBTightQ2_K11.4 GB309details
RTX 4070 Ti12 GBTightQ2_K11.4 GB309details
RTX 4070 Ti Super16 GBFitsQ2_K11.4 GB412details
RTX 408016 GBFitsQ2_K11.4 GB440details
RTX 4080 Super16 GBFitsQ2_K11.4 GB452details
RTX 50608 GBNo———details
RTX 507012 GBTightQ2_K11.4 GB412details
RTX 508016 GBFitsQ2_K11.4 GB589details
2x RTX 30902×24 GBFitsQ8_030.8 GB199details
2x RTX 40902×24 GBFitsQ8_030.8 GB214details
2x RTX 50902×32 GBFitsQ8_030.8 GB381details
RTX A600048 GBFitsQ8_030.8 GB163details
RTX 6000 Ada48 GBFitsQ8_030.8 GB204details
RTX PRO 6000 Blackwell96 GBFitsF1656.9 GB203details
L40S48 GBFitsQ8_030.8 GB184details
A100 40GB40 GBFitsQ8_030.8 GB331details
A100 80GB80 GBFitsF1656.9 GB231details
H100 PCIe80 GBFitsF1656.9 GB226details
H100 SXM80 GBFitsF1656.9 GB379details
H200141 GBFitsF1656.9 GB543details
RX 76008 GBNo———details
RX 7700 XT12 GBTightQ2_K11.4 GB265details
RX 7800 XT16 GBFitsQ2_K11.4 GB383details
RX 7900 GRE16 GBFitsQ2_K11.4 GB353details
RX 7900 XT20 GBFitsQ3_K_M14.2 GB385details
RX 907016 GBFitsQ2_K11.4 GB393details
RX 9070 XT16 GBFitsQ2_K11.4 GB393details
Ryzen AI Max+ 395 128GB128 GBFitsF1656.9 GB29details
Arc A770 16GB16 GBFitsQ2_K11.4 GB344details
Mac M1 16GB16 GBNo———details
Mac M2 24GB24 GBFitsQ3_K_M14.2 GB48details
Mac M3 24GB24 GBFitsQ3_K_M14.2 GB48details
Mac M4 16GB16 GBNo———details
Mac M4 32GB32 GBFitsQ4_K_M18.3 GB44details
Mac M1 Pro 32GB32 GBFitsQ4_K_M18.3 GB73details
Mac M3 Pro 36GB36 GBFitsQ5_K_M21.2 GB47details
Mac M4 Pro 24GB24 GBFitsQ3_K_M14.2 GB131details
Mac M4 Pro 64GB64 GBFitsQ8_030.8 GB58details
Mac M1 Max 64GB64 GBFitsQ8_030.8 GB85details
Mac M2 Max 96GB96 GBFitsF1656.9 GB45details
Mac M3 Max 128GB128 GBFitsF1656.9 GB45details
Mac M4 Max 64GB64 GBFitsQ8_030.8 GB116details
Mac M2 Ultra 192GB192 GBFitsF1656.9 GB90details
Mac M3 Ultra 256GB256 GBFitsF1656.9 GB93details

Prefer an API?

Z.ai: GLM 4.7 Flash is on OpenRouter at $0.0605 per 1M input tokens and $0.40 per 1M output tokens. Price details and history →

Questions

How much VRAM does GLM 4.7 Flash need?

About 18.3 GB at 4-bit (Q4_K_M) with an 8K context: 17.2 GB of weights (real GGUF file size), 0.4 GB of KV cache and 0.7 GB of runtime overhead. At 8-bit it needs about 30.8 GB.

What is the smallest GPU that runs GLM 4.7 Flash?

At Q4_K_M and 8K context, the smallest single consumer GPU in our table that fits it is the RTX 3090 (24 GB).

Can I run GLM 4.7 Flash on a Mac?

Yes. At Q4_K_M with 8K context it fits on a Mac M4 32GB or larger, using the default macOS GPU memory limit.

Similar models

Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.

GLM Z1 32B 0414

33B · 19.5 GB at 4-bit

GLM 4 32B 0414

33B · 19.5 GB at 4-bit

GLM 4.6V Flash

10B · 6.7 GB at 4-bit

Gemma 4 31B IT

31B · 21.2 GB at 4-bit

Gemma 4 31B

31B · 20.7 GB at 4-bit

Qwen3 Coder 30B A3B Instruct

31B · 18.8 GB at 4-bit

Embed this

GLM 4.7 Flash: runs on 24 GB+ VRAM Free badge and "Will it run on my GPU?" widget for model cards, READMEs and blogs. No cookies, no tracking. All options.

Copy a snippet

Markdown badge

[![GLM 4.7 Flash: runs on 24 GB+ VRAM (RunsOnMy)](https://runsonmy.com/badge/glm-4-7-flash.svg)](https://runsonmy.com/model/glm-4-7-flash/)

Widget (script)

<div class="runsonmy-widget" data-model="glm-4-7-flash"><a href="https://runsonmy.com/model/glm-4-7-flash/">Will GLM 4.7 Flash run on my GPU? Check on RunsOnMy</a></div>
<script async src="https://runsonmy.com/embed.js"></script>

Widget (iframe)

<iframe src="https://runsonmy.com/embed/m/glm-4-7-flash/" width="100%" height="220" style="max-width:440px;border:0" loading="lazy" title="Will GLM 4.7 Flash run on my GPU? (RunsOnMy)"></iframe>

Model facts

Hugging Face repozai-org/GLM-4.7-Flash
Parameters31,221,488,576 (31B) · ~4.6B active (computed from config)
Layers / hidden size47 / 2048
AttentionMLA; 20 heads, 20 KV heads, head dim 102
KV cache per token (FP16)52.9 KiB
Max context202,752 tokens
Licensemit
Released on HFJan 19, 2026
Downloads (30d) / likes1,158,857 / 1,905

Sources: Hugging Face model API · config.json (zai-org/GLM-4.7-Flash) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.