internlm2 5 20b chat needs ~12.5 GB VRAM. RTX 4070 12GB has 12.0 GB. With Q2_K quantization, expect ~28 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
4.9 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
11.2 tok/s
TTFT
17223 ms
Safe context
4K
Memory
16.9 GB / 12.0 GB
Offload
30%
This setup is broadly balanced for this model.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | F | Too heavy | 13.1 tok/s | 8079 ms | 4K |
| Coding | F | Too heavy | 11.2 tok/s | 17223 ms | 4K |
| Agentic Coding | F | Too heavy | 8.6 tok/s | 32906 ms | 4K |
| Reasoning | F | Too heavy | 11.2 tok/s | 20354 ms | 4K |
| RAG | F | Too heavy | 8.6 tok/s | 41132 ms | 4K |
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 4070 12GB (12.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_KBest for your GPU | 2 | 7.8 GB | Low | C51 |
Q3_K_S | 3 | 9.8 GB | Low | F0 |
NVFP4 | 4 | 11.2 GB | Medium | F0 |
Q4_K_M | 4 | 12.2 GB | Medium | F0 |
Q5_K_M | 5 | 14.4 GB | High | F0 |
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 startOpciones de mejora
RTX 5060 Ti 16GBMejor relación calidad-precioHace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.
Sube la velocidad estimada de decodificación alrededor de un 32%.
~$449 MSRP
RTX 4060 Ti 16GBMejora NVIDIAHace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.
Añade margen de memoria para más contexto y para que el modelo envejezca mejor.
~$499 MSRP
RTX 4000 Ada 20GBOpción económicaHace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.
Elimina el offload a memoria del sistema, que suele ser la mayor mejora individual en latencia y throughput.
~$1,250 MSRP
RTX 4090 24GBMayor saltoHace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.
Elimina el offload a memoria del sistema, que suele ser la mayor mejora individual en latencia y throughput.
~$1,599 MSRP
Yes, RTX 4070 12GB can run internlm2 5 20b chat at Q2_K quantization (Runs with offload (needs ~0.3 GB host RAM)). The recommended Q4_K_M requires 16.9 GB which exceeds available memory, but at Q2_K it needs only 12.5 GB. Expected decode speed: 28.1 tok/s.
internlm2 5 20b chat (20B parameters) requires approximately 16.9 GB at Q4_K_M quantization. On RTX 4070 12GB, it fits at Q2_K using 12.5 GB.
The recommended quantization is Q4_K_M, but on RTX 4070 12GB the best fitting quantization is Q2_K, which uses 12.5 GB.
On RTX 4070 12GB, internlm2 5 20b chat achieves approximately 28.1 tokens per second decode speed with a time-to-first-token of 6879ms using Q2_K quantization.
For coding workloads, internlm2 5 20b chat on RTX 4070 12GB receives a F grade with 11.2 tok/s and 4K context.
On RTX 4070 12GB, internlm2 5 20b chat can safely use up to 12K tokens of context at Q2_K quantization. The model's official context limit is —, but available memory constrains the safe maximum.
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
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-4070-12gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: