Can I run GLM-4.7-Flash on an RTX 5090 (32GB)?
Computed with the open FitLLM engine — accurate per-layer KV-cache modeling, not a naive estimate. Updated 2026-07-10.
Memory breakdown (Q4_K_M, F16 KV, 33K context)
| Model weights | 17.1 GB |
| KV cache | 1.7 GB |
| Runtime overhead + reserve | 5.3 GB |
| Total used | 24.0 / 32 GB |
| Free | 8.0 GB |
Max context that fits at Q4_K_M: ~105K tokens · with Q8 KV cache → ~157K tokens.
Every quantization on the RTX 5090
| Weight quant | Weights | Fits (KV F16) | Used @32K |
|---|---|---|---|
| Q4_K_M | 17.1 GB | ✅ up to 105K ctx | 24.0 / 32.0 GB |
| Q5_K_M | 19.9 GB | ✅ up to 69K ctx | 27.2 / 32.0 GB |
| Q6_K | 22.9 GB | ⚠️ up to 31K ctx | 30.6 / 32.0 GB |
| Q8_0 | 29.7 GB | ❌ won't fit | 38.1 / 32.0 GB |
| FP16 | 55.9 GB | ❌ won't fit | 67.5 / 32.0 GB |
Lower weight quants free memory at some output-quality cost — Q4 is the common sweet spot; below that quality drops faster.
KV cache is F16 here (llama.cpp default). Drop it to Q8/Q4 (-ctk/-ctv) for more context.
Embed this verdict
Live badge for your README or model card — recomputed by the engine, never stale:
[](https://fitllm.run/can-i-run/glm-4-7-flash-on-rtx-5090)
Or from your terminal (exit 0/1 — works as a pre-download guard):
npx fitllm "GLM-4.7-Flash" --gpu "RTX 5090"Why most VRAM calculators get this wrong
GLM-4.7-Flash uses MLA (Multi-head Latent Attention): K/V are compressed into a single low-rank latent (512 + 64 RoPE dims) shared across all heads — cached once, not per-head K and V. Naive "2 × heads × head_dim × layers" formulas over-count its KV cache by an order of magnitude.
Other options
same GPU Models that fit on the RTX 5090: GLM-4.7-Flash, gpt-oss-20b, Qwen 3.6 27B, Qwen 3.6 35B-A3B, Qwen-AgentWorld-35B-A3B, Gemma 4 e2b, Gemma 4 e4b, Gemma 4 12b, Gemma 4 26b A4B, Gemma 4 31b, Llama-3.2-3B-Instruct, Llama-3.1-8B-Instruct, Qwen3-0.6B, Qwen3-1.7B, Llama-3.2-1B-Instruct, Gemma-3-1B-it.
same model GPUs that run GLM-4.7-Flash: RTX 5090 (32GB), RTX 4090 (24GB), RTX 3090 (24GB), RTX 3090 Ti (24GB), RTX 6000 Ada (48GB), RTX PRO 6000 Blackwell (96GB), RX 7900 XTX (24GB), Radeon PRO W7900 (48GB), 2× RTX 3090 (48GB), 2× RTX 4090 (48GB), 4× RTX 3090 (96GB), A100 40GB (40GB), A100 80GB (80GB), H100 80GB (80GB), H200 141GB (141GB), B200 (192GB).
Reproduce it
GLM-4.7-Flash = 30B (3B active, MoE), 47 layers. The RTX 5090 has 32GB / 1792GB/s. Same math, open source: fitllm-engine. GGUF bpw from llama.cpp.
All numbers are computed by the open-source fitllm-engine (MIT) from official model config.json values — reproduce or audit them yourself. Estimates; real usage varies with runtime (llama.cpp / MLX / Ollama), driver and display. Found a mismatch? Report it. · FitLLM home