Can I run GLM 4 9B locally?
GLM 4 9B by zai-org has 9.4B parameters. At 4-bit with an 8K context it needs about 6.8 GB of GPU memory. It fits on 65 of 65 GPUs and Macs we track. See all models that fit in 8 GB of VRAM.
Memory needed by quant and context length
GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from mradermacher/glm-4-9b-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.
| Quant | Quality | 4K ctx | 8K ctx |
|---|---|---|---|
| 2-bit (Q2_K) • | rough | 4.6 GB | 4.7 GB |
| 3-bit (Q3_K_M) • | usable | 5.6 GB | 5.7 GB |
| 4-bit (Q4_K_M) • | good, most popular | 6.7 GB | 6.8 GB |
| 5-bit (Q5_K_M) • | very good | 7.5 GB | 7.7 GB |
| 6-bit (Q6_K) • | near lossless | 8.5 GB | 8.7 GB |
| 8-bit (Q8_0) • | effectively lossless | 10.2 GB | 10.3 GB |
| 16-bit (F16/BF16) • | original weights | 18.4 GB | 18.5 GB |
GLM 4 9B on Ollama: download size and VRAM
ollama run glm4:9b-text-q4_K_M | Source | File | Download size | GPU memory at 8K ctx (est.) |
|---|---|---|---|
| Ollama download size | glm4:9b-text-q4_K_M (Q4_K_M) | 6.3 GB | 6.9 GB |
| Our GGUF (Hugging Face) | mradermacher/glm-4-9b-GGUF (Q4_K_M) | 6.3 GB | 6.8 GB |
Download sizes are decimal GB, as ollama.com lists them; memory figures on this site use binary GB (GiB). GPU memory for the Ollama tag is its file size plus this model's KV cache at 8K context and runtime overhead; Ollama's default context window may be smaller (set num_ctx to change it). Source: ollama.com/library/glm4:9b-text-q4_K_M, checked Nov 17, 2026. Refreshed weekly; shown only when the tag's architecture and parameter count match this model. All Ollama models with sizes and VRAM.
Which GPUs and Macs run GLM 4 9B?
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).
| Hardware | Memory | Fits? | Best quant | Needs | Max tok/s (est.) | Details |
|---|---|---|---|---|---|---|
| RTX 3060 12GB | 12 GB | Fits | Q6_K | 8.7 GB | 44 | details |
| RTX 4060 Ti 16GB | 16 GB | Fits | Q8_0 | 10.3 GB | 29 | details |
| RTX 3090 | 24 GB | Fits | F16 | 18.5 GB | 50 | details |
| RTX 4090 | 24 GB | Fits | F16 | 18.5 GB | 54 | details |
| RTX 5090 | 32 GB | Fits | F16 | 18.5 GB | 95 | details |
| RTX 5070 Ti | 16 GB | Fits | Q8_0 | 10.3 GB | 90 | details |
| RX 7900 XTX | 24 GB | Fits | F16 | 18.5 GB | 51 | details |
| Mac M4 Pro 48GB | 48 GB | Fits | F16 | 18.5 GB | 15 | details |
| Mac M4 Max 128GB | 128 GB | Fits | F16 | 18.5 GB | 29 | details |
| Mac M3 Ultra 512GB | 512 GB | Fits | F16 | 18.5 GB | 44 | details |
| DGX Spark | 128 GB | Fits | F16 | 18.5 GB | 15 | details |
| RTX 4070 | 12 GB | Fits | Q6_K | 8.7 GB | 61 | details |
| RTX 5060 Ti 16GB | 16 GB | Fits | Q8_0 | 10.3 GB | 45 | details |
| RTX 4060 | 8 GB | Fits | Q4_K_M | 6.8 GB | 44 | details |
| Arc B580 | 12 GB | Fits | Q6_K | 8.7 GB | 55 | details |
| RTX 3060 Ti | 8 GB | Fits | Q4_K_M | 6.8 GB | 72 | details |
| RTX 3070 | 8 GB | Fits | Q4_K_M | 6.8 GB | 72 | details |
| RTX 3080 10GB | 10 GB | Fits | Q5_K_M | 7.7 GB | 106 | details |
| RTX 3080 12GB | 12 GB | Fits | Q6_K | 8.7 GB | 110 | details |
| RTX 3090 Ti | 24 GB | Fits | F16 | 18.5 GB | 54 | details |
| RTX 4060 Ti 8GB | 8 GB | Fits | Q4_K_M | 6.8 GB | 46 | details |
| RTX 4070 Super | 12 GB | Fits | Q6_K | 8.7 GB | 61 | details |
| RTX 4070 Ti | 12 GB | Fits | Q6_K | 8.7 GB | 61 | details |
| RTX 4070 Ti Super | 16 GB | Fits | Q8_0 | 10.3 GB | 67 | details |
| RTX 4080 | 16 GB | Fits | Q8_0 | 10.3 GB | 72 | details |
| RTX 4080 Super | 16 GB | Fits | Q8_0 | 10.3 GB | 74 | details |
| RTX 5060 | 8 GB | Fits | Q4_K_M | 6.8 GB | 72 | details |
| RTX 5070 | 12 GB | Fits | Q6_K | 8.7 GB | 81 | details |
| RTX 5080 | 16 GB | Fits | Q8_0 | 10.3 GB | 96 | details |
| 2x RTX 3090 | 2×24 GB | Fits | F16 | 18.5 GB | 50 | details |
| 2x RTX 4090 | 2×24 GB | Fits | F16 | 18.5 GB | 54 | details |
| 2x RTX 5090 | 2×32 GB | Fits | F16 | 18.5 GB | 95 | details |
| RTX A6000 | 48 GB | Fits | F16 | 18.5 GB | 41 | details |
| RTX 6000 Ada | 48 GB | Fits | F16 | 18.5 GB | 51 | details |
| RTX PRO 6000 Blackwell | 96 GB | Fits | F16 | 18.5 GB | 95 | details |
| L40S | 48 GB | Fits | F16 | 18.5 GB | 46 | details |
| A100 40GB | 40 GB | Fits | F16 | 18.5 GB | 83 | details |
| A100 80GB | 80 GB | Fits | F16 | 18.5 GB | 108 | details |
| H100 PCIe | 80 GB | Fits | F16 | 18.5 GB | 106 | details |
| H100 SXM | 80 GB | Fits | F16 | 18.5 GB | 178 | details |
| H200 | 141 GB | Fits | F16 | 18.5 GB | 255 | details |
| RX 7600 | 8 GB | Fits | Q4_K_M | 6.8 GB | 46 | details |
| RX 7700 XT | 12 GB | Fits | Q6_K | 8.7 GB | 52 | details |
| RX 7800 XT | 16 GB | Fits | Q8_0 | 10.3 GB | 62 | details |
| RX 7900 GRE | 16 GB | Fits | Q8_0 | 10.3 GB | 58 | details |
| RX 7900 XT | 20 GB | Fits | Q8_0 | 10.3 GB | 80 | details |
| RX 9070 | 16 GB | Fits | Q8_0 | 10.3 GB | 64 | details |
| RX 9070 XT | 16 GB | Fits | Q8_0 | 10.3 GB | 64 | details |
| Ryzen AI Max+ 395 128GB | 128 GB | Fits | F16 | 18.5 GB | 14 | details |
| Arc A770 16GB | 16 GB | Fits | Q8_0 | 10.3 GB | 56 | details |
| Mac M1 16GB | 16 GB | Fits | Q6_K | 8.7 GB | 8.2 | details |
| Mac M2 24GB | 24 GB | Fits | Q8_0 | 10.3 GB | 10 | details |
| Mac M3 24GB | 24 GB | Fits | Q8_0 | 10.3 GB | 10 | details |
| Mac M4 16GB | 16 GB | Fits | Q6_K | 8.7 GB | 15 | details |
| Mac M4 32GB | 32 GB | Fits | F16 | 18.5 GB | 6.4 | details |
| Mac M1 Pro 32GB | 32 GB | Fits | F16 | 18.5 GB | 11 | details |
| Mac M3 Pro 36GB | 36 GB | Fits | F16 | 18.5 GB | 8.0 | details |
| Mac M4 Pro 24GB | 24 GB | Fits | Q8_0 | 10.3 GB | 27 | details |
| Mac M4 Pro 64GB | 64 GB | Fits | F16 | 18.5 GB | 15 | details |
| Mac M1 Max 64GB | 64 GB | Fits | F16 | 18.5 GB | 21 | details |
| Mac M2 Max 96GB | 96 GB | Fits | F16 | 18.5 GB | 21 | details |
| Mac M3 Max 128GB | 128 GB | Fits | F16 | 18.5 GB | 21 | details |
| Mac M4 Max 64GB | 64 GB | Fits | F16 | 18.5 GB | 29 | details |
| Mac M2 Ultra 192GB | 192 GB | Fits | F16 | 18.5 GB | 43 | details |
| Mac M3 Ultra 256GB | 256 GB | Fits | F16 | 18.5 GB | 44 | details |
Questions
How much VRAM does GLM 4 9B need?
About 6.8 GB at 4-bit (Q4_K_M) with an 8K context: 5.8 GB of weights (real GGUF file size), 0.3 GB of KV cache and 0.7 GB of runtime overhead. At 8-bit it needs about 10.3 GB.
What is the smallest GPU that runs GLM 4 9B?
At Q4_K_M and 8K context, the smallest single consumer GPU in our table that fits it is the RTX 4060 (8 GB).
How big is the Ollama download for GLM 4 9B?
6.3GB for the glm4:9b-text-q4_K_M tag (Q4_K_M), as listed on ollama.com. Run it with "ollama run glm4:9b-text-q4_K_M". With an 8K context, plan on about 6.9 GB of GPU memory.
Can I run GLM 4 9B on a Mac?
Yes. At Q4_K_M with 8K context it fits on a Mac M1 16GB 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 4.6V Flash
10B · 6.7 GB at 4-bitGLM 4.1V 9B Thinking
10B · 6.7 GB at 4-bitGLM 4.7 Flash
31B · 18.3 GB at 4-bitMiMo V2.6 Distill Qwen 9B
9.4B · 6.6 GB at 4-bitSenseNova Loop 9B
9.4B · 6.4 GB at 4-bitQwen3.5 9B
9.7B · 6.9 GB at 4-bitEmbed this
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
[](https://runsonmy.com/model/glm-4-9b/) Widget (script)
<div class="runsonmy-widget" data-model="glm-4-9b"><a href="https://runsonmy.com/model/glm-4-9b/">Will GLM 4 9B 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-4-9b/" width="100%" height="220" style="max-width:440px;border:0" loading="lazy" title="Will GLM 4 9B run on my GPU? (RunsOnMy)"></iframe> Model facts
| Hugging Face repo | zai-org/glm-4-9b |
| Parameters | 9,399,951,392 (9.4B) |
| Layers / hidden size | 40 / 4096 |
| Attention | GQA; 32 heads, 2 KV heads, head dim 128 |
| KV cache per token (FP16) | 40.0 KiB |
| Max context | 8,192 tokens |
| License | other |
| Released on HF | Jun 4, 2024 |
| Downloads (30d) / likes | 23,018 / 145 |
Sources: Hugging Face model API · config.json (zai-org/glm-4-9b) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.