RTX 3090 24GBBudget pick24 GB VRAM (+4)936 GB/s (+576)
C
Raises estimated decode speed by about 133%.53.7 tok/s decode
Raises estimated decode speed by about 133%.
~$1,499 MSRP
internlm2 5 20b chat needs ~17.7 GB VRAM. RTX 4000 Ada 20GB has 20.0 GB. With Q4_K_M quantization, expect ~23 tok/s.
Operating mode
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
Fit status
Tight fit
Decode
23.0 tok/s
TTFT
8411 ms
Safe context
31K
Memory
17.7 GB / 20.0 GB
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Tight fit | 23.0 tok/s | 4588 ms | 31K |
| Coding | C | Tight fit | 23.0 tok/s | 8411 ms | 31K |
| Agentic Coding | C | Runs with offload (needs ~0.1 GB host RAM) | 17.1 tok/s | 16464 ms | 31K |
| Reasoning | C | Tight fit | 23.0 tok/s | 9941 ms | 31K |
| RAG | C | Runs with offload (needs ~0.1 GB host RAM) | 17.1 tok/s | 20580 ms | 31K |
Inference speed
Estimated decode speed (tokens/sec) for internlm2 5 20b chat at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~98 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
| RTX 5090 32GB | 32 GB | Q4_K_M | 98.4 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 62.8 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 56.7 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 53.7 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 45.6 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 38.0 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 36.1 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 35.6 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 35.6 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 31.7 | Heavy offload |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 22.4 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 19.7 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 18.0 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 11.2 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 7.1 | Too big |
| RTX 4060 8GB | 8 GB | Q4_K_M | 2.6 | Too big |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
How internlm2 5 20b chat (20B params) fits at each quantization level on RTX 4000 Ada 20GB (20.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 7.8 GB | Low | C49 |
Q3_K_S | 3 | 9.8 GB | Low | C51 |
NVFP4 | 4 | 11.2 GB | Medium | C50 |
Q4_K_M | 4 | 12.2 GB | Medium | C50 |
Q5_K_MBest for your GPU | 5 | 14.4 GB | High | C50 |
Q6_K | 6 | 16.4 GB | High | F0 |
Q8_0 | 8 | 21.4 GB | Very High | F0 |
F16 | 16 | 41.0 GB | Maximum | F0 |
Copy-paste commands to run internlm2 5 20b chat on your machine.
Run
lms load hf-bartowski--internlm2-5-20b-chat-gguf && lms server startUpgrade options
RTX 3090 24GBBudget pickRaises estimated decode speed by about 133%.
~$1,499 MSRP
RTX 4090 24GBBest valueRaises estimated decode speed by about 173%.
~$1,599 MSRP
RTX PRO 4000 Blackwell 24GBNVIDIA upgradeRaises estimated decode speed by about 101%.
~$1,599 MSRP
Yes, RTX 4000 Ada 20GB can run internlm2 5 20b chat with a C grade (Tight fit). Expected decode speed: 23.0 tok/s.
internlm2 5 20b chat (20B parameters) requires approximately 17.7 GB of memory with Q4_K_M quantization.
The recommended quantization for internlm2 5 20b chat is Q4_K_M, which balances quality and memory efficiency.
On RTX 4000 Ada 20GB, internlm2 5 20b chat achieves approximately 23.0 tokens per second decode speed with a time-to-first-token of 8411ms using Q4_K_M quantization.
For coding workloads, internlm2 5 20b chat on RTX 4000 Ada 20GB receives a C grade with 23.0 tok/s and 31K context.
On RTX 4000 Ada 20GB, internlm2 5 20b chat can safely use up to 31K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-bartowski--internlm2-5-20b-chat-gguf-on-rtx-4000-ada-20gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: